Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0503. Min Range: -5.0503
Max Act: 5.0503. Min Act: -0.1700
Data Index: 2725100 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.9878. Min Act: -0.1700
Data Index: 6085914 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.9566. Min Act: -0.1700
Data Index: 3712233 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.9566. Min Act: -0.1700
Data Index: 6548469 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.9566. Min Act: -0.1700
Data Index: 8181331 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.9253. Min Act: -0.1700
Data Index: 6271125 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.9253. Min Act: -0.1700
Data Index: 606697 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 4366594 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.9253. Min Act: -0.1700
Data Index: 2031126 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 1060436 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 6343911 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 6681401 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 7612789 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 7613126 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8941. Min Act: -0.1700
Data Index: 3179741 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8628. Min Act: -0.1700
Data Index: 7697342 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8628. Min Act: -0.1700
Data Index: 997044 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8628. Min Act: -0.1700
Data Index: 953928 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4312045 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0503. Min Range: -5.0503
Max Act: 4.8316. Min Act: -0.1700
Data Index: 2600005 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19