Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4272 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3226. Min Range: -12.3226
Max Act: 12.3226. Min Act: -0.1700
Data Index: 2980411 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.8851. Min Act: -0.1700
Data Index: 6979391 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.6351. Min Act: -0.1700
Data Index: 7342833 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.5726. Min Act: -0.1700
Data Index: 3075149 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.5101. Min Act: -0.1700
Data Index: 2389028 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.3851. Min Act: -0.1700
Data Index: 4902289 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.3226. Min Act: -0.1700
Data Index: 2014924 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.1351. Min Act: -0.1700
Data Index: 3931676 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.1351. Min Act: -0.1700
Data Index: 4640483 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.0726. Min Act: -0.1700
Data Index: 4111181 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3226. Min Range: -12.3226
Max Act: 11.0101. Min Act: -0.1700
Data Index: 497915 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.9476. Min Act: -0.1700
Data Index: 4277134 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.9476. Min Act: -0.1700
Data Index: 8359723 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.9476. Min Act: -0.1700
Data Index: 4085143 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.8851. Min Act: -0.1700
Data Index: 1688028 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.8851. Min Act: -0.1700
Data Index: 330127 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.8226. Min Act: -0.1700
Data Index: 3163420 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.7601. Min Act: -0.1700
Data Index: 6454268 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.7601. Min Act: -0.1700
Data Index: 4148471 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3226. Min Range: -12.3226
Max Act: 10.7601. Min Act: -0.1700
Data Index: 3239729 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19