Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4843 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.3454. Min Act: -0.1700
Data Index: 2298811 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.2517. Min Act: -0.1700
Data Index: 30853 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.2517. Min Act: -0.1700
Data Index: 5092199 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.1892. Min Act: -0.1700
Data Index: 7442449 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.0954. Min Act: -0.1700
Data Index: 2878318 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.0642. Min Act: -0.1700
Data Index: 6402749 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.0642. Min Act: -0.1700
Data Index: 56693 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.0329. Min Act: -0.1700
Data Index: 1334680 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.0017. Min Act: -0.1700
Data Index: 627524 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3454. Min Range: -5.3454
Max Act: 5.0017. Min Act: -0.1700
Data Index: 366473 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9704. Min Act: -0.1700
Data Index: 676209 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9704. Min Act: -0.1700
Data Index: 7990639 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9704. Min Act: -0.1700
Data Index: 3672614 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9704. Min Act: -0.1700
Data Index: 4515502 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9704. Min Act: -0.1700
Data Index: 8039002 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9392. Min Act: -0.1700
Data Index: 272252 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9392. Min Act: -0.1700
Data Index: 2347390 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9392. Min Act: -0.1700
Data Index: 2594505 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9392. Min Act: -0.1700
Data Index: 1103507 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3454. Min Range: -5.3454
Max Act: 4.9392. Min Act: -0.1700
Data Index: 6321530 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19