Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.9510. Min Act: -0.1700
Data Index: 858993 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.6385. Min Act: -0.1700
Data Index: 3863248 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.6072. Min Act: -0.1700
Data Index: 2715576 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.6072. Min Act: -0.1700
Data Index: 2486459 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.5760. Min Act: -0.1700
Data Index: 4591848 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.5447. Min Act: -0.1700
Data Index: 7858529 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.4822. Min Act: -0.1700
Data Index: 7975085 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.4822. Min Act: -0.1700
Data Index: 8185234 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.4510. Min Act: -0.1700
Data Index: 1854484 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.4510. Min Act: -0.1700
Data Index: 350542 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.4197. Min Act: -0.1700
Data Index: 3980159 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.3572. Min Act: -0.1700
Data Index: 5164249 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.3572. Min Act: -0.1700
Data Index: 4737590 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.3572. Min Act: -0.1700
Data Index: 4001475 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.3260. Min Act: -0.1700
Data Index: 8036504 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.3260. Min Act: -0.1700
Data Index: 7975816 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.3260. Min Act: -0.1700
Data Index: 2337713 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.2947. Min Act: -0.1700
Data Index: 7844510 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.2947. Min Act: -0.1700
Data Index: 7095505 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9510. Min Range: -6.9510
Max Act: 6.2947. Min Act: -0.1700
Data Index: 4925702 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19