Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6602. Min Range: -8.6602
Max Act: 8.6602. Min Act: -0.1700
Data Index: 3762970 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.7539. Min Act: -0.1700
Data Index: 653458 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.7227. Min Act: -0.1700
Data Index: 7085009 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.6289. Min Act: -0.1700
Data Index: 8729467 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.6289. Min Act: -0.1700
Data Index: 1216076 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.5977. Min Act: -0.1700
Data Index: 7744622 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.5664. Min Act: -0.1700
Data Index: 3798412 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.5352. Min Act: -0.1700
Data Index: 5137066 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.4727. Min Act: -0.1700
Data Index: 7525886 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.5039. Min Act: -0.1700
Data Index: 4036311 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.4414. Min Act: -0.1700
Data Index: 5137065 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.4414. Min Act: -0.1700
Data Index: 5082238 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.4102. Min Act: -0.1700
Data Index: 1550993 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.4102. Min Act: -0.1700
Data Index: 6134091 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.4102. Min Act: -0.1700
Data Index: 3065495 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.3477. Min Act: -0.1700
Data Index: 7822688 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.3164. Min Act: -0.1700
Data Index: 3018032 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.3164. Min Act: -0.1700
Data Index: 2111312 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.3164. Min Act: -0.1700
Data Index: 3574723 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6602. Min Range: -8.6602
Max Act: 7.2852. Min Act: -0.1700
Data Index: 3861645 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19