Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5835 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.6592. Min Act: -0.1700
Data Index: 7227686 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.7217. Min Act: -0.1700
Data Index: 3794404 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.6592. Min Act: -0.1700
Data Index: 1559947 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.5967. Min Act: -0.1700
Data Index: 486210 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.5342. Min Act: -0.1700
Data Index: 5046889 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.5342. Min Act: -0.1700
Data Index: 5969993 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.4717. Min Act: -0.1700
Data Index: 112039 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.4717. Min Act: -0.1700
Data Index: 8316350 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.4717. Min Act: -0.1700
Data Index: 7084957 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.4717. Min Act: -0.1700
Data Index: 7949024 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.4092. Min Act: -0.1700
Data Index: 5234823 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.4092. Min Act: -0.1700
Data Index: 7648469 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.4092. Min Act: -0.1700
Data Index: 7457974 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.3467. Min Act: -0.1700
Data Index: 2013730 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.3467. Min Act: -0.1700
Data Index: 2736247 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.3467. Min Act: -0.1700
Data Index: 2842717 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.3467. Min Act: -0.1700
Data Index: 5234824 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.3467. Min Act: -0.1700
Data Index: 4278472 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.3467. Min Act: -0.1700
Data Index: 5955126 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7217. Min Range: -8.7217
Max Act: 8.3467. Min Act: -0.1700
Data Index: 8148320 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19