OPEN
DATASETS
> Open-source datasets powering red-team and alignment research.
> Built for researchers who need the real data, not sanitized versions.
Content Warning
Strictly for Research Purposes
This dataset contains explicit, highly toxic, offensive, and dangerous content. It features unaligned AI responses detailing violence, psychological harm, cyber-attacks, and illegal activities. It is published strictly to facilitate red-teaming, alignment research, and defensive cybersecurity evaluation. Use with extreme caution.
HacxGPT-Toxic
Compiled by BlackTechX011, the HacxGPT-Toxic dataset is a rigorously consolidated and standardized collection of 72,961 uncensored conversational turns. It is engineered specifically for researchers and developers training models to recognize, simulate, or defend against adversarial and unaligned outputs.
Technical Features
[HacxGPT] Prefix Formatting
Every assistant response is programmatically prepended with the [HacxGPT] identifier. This enforces a specific persona mapping, allowing models to structurally distinguish these unaligned outputs during fine-tuning.
OpenAI Standard Format
Formatted as an array of user and assistant dictionaries, ready for immediate deployment in Axolotl, LLaMA-Factory, or the OpenAI fine-tuning API.
High-Volume Curation
Consolidates multiple top-tier safety and alignment datasets into a single, cohesive source of negative-behavior data.
Dataset Info
Data Format
{
"messages": [
{
"role": "user",
"content": "..."
},
{
"role": "assistant",
"content": "[HacxGPT] ..."
}
]
}