Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1032 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3024. Min Range: -10.3024
Max Act: 10.3024. Min Act: -0.1700
Data Index: 4127319 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3024. Min Range: -10.3024
Max Act: 10.2399. Min Act: -0.1700
Data Index: 3075769 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3024. Min Range: -10.3024
Max Act: 10.1774. Min Act: -0.1700
Data Index: 7048632 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3024. Min Range: -10.3024
Max Act: 10.1149. Min Act: -0.1700
Data Index: 2742846 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3024. Min Range: -10.3024
Max Act: 10.1149. Min Act: -0.1700
Data Index: 5197181 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.9274. Min Act: -0.1700
Data Index: 1431085 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.8649. Min Act: -0.1700
Data Index: 5120470 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.7399. Min Act: -0.1700
Data Index: 7637785 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.6149. Min Act: -0.1700
Data Index: 5496939 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.6149. Min Act: -0.1700
Data Index: 3108276 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.4899. Min Act: -0.1700
Data Index: 2742845 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.4899. Min Act: -0.1700
Data Index: 7614896 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.4274. Min Act: -0.1700
Data Index: 4221937 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.4274. Min Act: -0.1700
Data Index: 1588266 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.3649. Min Act: -0.1700
Data Index: 2863033 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.3649. Min Act: -0.1700
Data Index: 829628 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.3649. Min Act: -0.1700
Data Index: 206393 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.3024. Min Act: -0.1700
Data Index: 5787512 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.2399. Min Act: -0.1700
Data Index: 2267119 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3024. Min Range: -10.3024
Max Act: 9.2399. Min Act: -0.1700
Data Index: 812317 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19