Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 906 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.9190. Min Act: -0.1700
Data Index: 455069 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.6690. Min Act: -0.1700
Data Index: 6692203 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.5440. Min Act: -0.1700
Data Index: 7825293 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.6065. Min Act: -0.1700
Data Index: 8140309 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.5440. Min Act: -0.1700
Data Index: 7197023 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.3565. Min Act: -0.1700
Data Index: 4280764 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.3565. Min Act: -0.1700
Data Index: 3900055 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.3565. Min Act: -0.1700
Data Index: 792466 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.2940. Min Act: -0.1700
Data Index: 3882334 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.1690. Min Act: -0.1700
Data Index: 2476768 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.3565. Min Act: -0.1700
Data Index: 7839153 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.2315. Min Act: -0.1700
Data Index: 5895379 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.3565. Min Act: -0.1700
Data Index: 6093920 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.2315. Min Act: -0.1700
Data Index: 616895 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.2315. Min Act: -0.1700
Data Index: 2489177 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.1065. Min Act: -0.1700
Data Index: 3881637 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.1690. Min Act: -0.1700
Data Index: 4875572 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.1690. Min Act: -0.1700
Data Index: 2146011 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.1690. Min Act: -0.1700
Data Index: 5361616 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9190. Min Range: -11.9190
Max Act: 11.1690. Min Act: -0.1700
Data Index: 7625485 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19