Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.7772. Min Act: -0.1700
Data Index: 2131121 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.5584. Min Act: -0.1700
Data Index: 3226415 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.5272. Min Act: -0.1700
Data Index: 1036252 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.4334. Min Act: -0.1700
Data Index: 3471185 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.4022. Min Act: -0.1700
Data Index: 8395451 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.1834. Min Act: -0.1700
Data Index: 678157 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.1834. Min Act: -0.1700
Data Index: 2990415 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.2147. Min Act: -0.1700
Data Index: 1686375 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.1834. Min Act: -0.1700
Data Index: 8372055 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.0897. Min Act: -0.1700
Data Index: 6064126 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.0897. Min Act: -0.1700
Data Index: 2283692 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.0584. Min Act: -0.1700
Data Index: 1375783 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7772. Min Range: -7.7772
Max Act: 6.9959. Min Act: -0.1700
Data Index: 5983605 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7772. Min Range: -7.7772
Max Act: 7.0272. Min Act: -0.1700
Data Index: 5305408 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7772. Min Range: -7.7772
Max Act: 6.9959. Min Act: -0.1700
Data Index: 1103153 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7772. Min Range: -7.7772
Max Act: 6.9959. Min Act: -0.1700
Data Index: 828917 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7772. Min Range: -7.7772
Max Act: 6.9959. Min Act: -0.1700
Data Index: 2397579 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7772. Min Range: -7.7772
Max Act: 6.9959. Min Act: -0.1700
Data Index: 5916475 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7772. Min Range: -7.7772
Max Act: 6.9647. Min Act: -0.1700
Data Index: 4412027 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7772. Min Range: -7.7772
Max Act: 6.9647. Min Act: -0.1700
Data Index: 7677411 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19