Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2401 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8675. Min Act: -0.1700
Data Index: 5219069 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8590. Min Act: -0.1700
Data Index: 4993228 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8505. Min Act: -0.1700
Data Index: 1197215 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8167. Min Act: -0.1700
Data Index: 4026815 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8251. Min Act: -0.1700
Data Index: 5594695 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8167. Min Act: -0.1700
Data Index: 8832751 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8167. Min Act: -0.1700
Data Index: 2622736 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.8083. Min Act: -0.1700
Data Index: 3741371 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7915. Min Act: -0.1700
Data Index: 1367085 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7999. Min Act: -0.1700
Data Index: 6485798 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7999. Min Act: -0.1700
Data Index: 7289121 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7999. Min Act: -0.1700
Data Index: 7477898 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7999. Min Act: -0.1700
Data Index: 6419889 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7915. Min Act: -0.1700
Data Index: 7065813 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7915. Min Act: -0.1700
Data Index: 5543485 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7832. Min Act: -0.1700
Data Index: 6087077 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7915. Min Act: -0.1700
Data Index: 547512 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7748. Min Act: -0.1700
Data Index: 7537827 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7748. Min Act: -0.1700
Data Index: 3625104 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8675. Min Range: -0.8675
Max Act: 0.7748. Min Act: -0.1700
Data Index: 648768 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19