Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2380 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3225. Min Range: -5.3225
Max Act: 5.3225. Min Act: -0.1700
Data Index: 8456249 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3225. Min Range: -5.3225
Max Act: 5.0412. Min Act: -0.1700
Data Index: 8072514 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3225. Min Range: -5.3225
Max Act: 5.0725. Min Act: -0.1700
Data Index: 4249461 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3225. Min Range: -5.3225
Max Act: 5.1037. Min Act: -0.1700
Data Index: 6362497 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3225. Min Range: -5.3225
Max Act: 5.0100. Min Act: -0.1700
Data Index: 297995 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3225. Min Range: -5.3225
Max Act: 5.0725. Min Act: -0.1700
Data Index: 8223275 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3225. Min Range: -5.3225
Max Act: 5.0412. Min Act: -0.1700
Data Index: 997888 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.9787. Min Act: -0.1700
Data Index: 5005546 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.9787. Min Act: -0.1700
Data Index: 7927084 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.9787. Min Act: -0.1700
Data Index: 1681887 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.9475. Min Act: -0.1700
Data Index: 6345957 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.9162. Min Act: -0.1700
Data Index: 7581699 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.9162. Min Act: -0.1700
Data Index: 109556 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.9162. Min Act: -0.1700
Data Index: 3622246 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.8850. Min Act: -0.1700
Data Index: 3379091 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.8537. Min Act: -0.1700
Data Index: 3931271 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.7912. Min Act: -0.1700
Data Index: 317399 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.8225. Min Act: -0.1700
Data Index: 4930866 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.7600. Min Act: -0.1700
Data Index: 6458112 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3225. Min Range: -5.3225
Max Act: 4.7600. Min Act: -0.1700
Data Index: 7499201 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19