Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.7418. Min Act: -0.1700
Data Index: 6859418 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.6793. Min Act: -0.1700
Data Index: 530648 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.6793. Min Act: -0.1700
Data Index: 4184863 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.6480. Min Act: -0.1700
Data Index: 6423897 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.6168. Min Act: -0.1700
Data Index: 1928823 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.6168. Min Act: -0.1700
Data Index: 85033 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.5543. Min Act: -0.1700
Data Index: 7114715 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.5855. Min Act: -0.1700
Data Index: 6827547 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.5230. Min Act: -0.1700
Data Index: 4252314 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.5230. Min Act: -0.1700
Data Index: 1989481 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.5230. Min Act: -0.1700
Data Index: 2638304 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4918. Min Act: -0.1700
Data Index: 1991667 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4605. Min Act: -0.1700
Data Index: 2890328 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4605. Min Act: -0.1700
Data Index: 2563686 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4605. Min Act: -0.1700
Data Index: 6827546 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4605. Min Act: -0.1700
Data Index: 3867110 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.3980. Min Act: -0.1700
Data Index: 3206916 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4293. Min Act: -0.1700
Data Index: 6223850 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4293. Min Act: -0.1700
Data Index: 1175075 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7418. Min Range: -5.7418
Max Act: 5.4293. Min Act: -0.1698
Data Index: 471347 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19