Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2881 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.6962. Min Act: -0.1700
Data Index: 747807 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.6337. Min Act: -0.1700
Data Index: 3091382 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.5711. Min Act: -0.1700
Data Index: 7244360 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.5399. Min Act: -0.1700
Data Index: 846044 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.5086. Min Act: -0.1700
Data Index: 2903449 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4461. Min Act: -0.1700
Data Index: 7153070 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4774. Min Act: -0.1700
Data Index: 3065479 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4774. Min Act: -0.1700
Data Index: 4371810 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4774. Min Act: -0.1700
Data Index: 3267910 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4774. Min Act: -0.1700
Data Index: 4061701 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4774. Min Act: -0.1700
Data Index: 6318333 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.5086. Min Act: -0.1700
Data Index: 8434094 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4461. Min Act: -0.1700
Data Index: 256602 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4461. Min Act: -0.1700
Data Index: 1763530 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4461. Min Act: -0.1700
Data Index: 1246738 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4461. Min Act: -0.1700
Data Index: 850932 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4149. Min Act: -0.1700
Data Index: 6318332 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4149. Min Act: -0.1700
Data Index: 323819 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.4149. Min Act: -0.1700
Data Index: 7817946 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6962. Min Range: -4.6962
Max Act: 4.3836. Min Act: -0.1700
Data Index: 6409745 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19