Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0523. Min Range: -4.0523
Max Act: 4.0523. Min Act: -0.1700
Data Index: 1804227 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.9898. Min Act: -0.1700
Data Index: 5169397 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.9585. Min Act: -0.1700
Data Index: 4833521 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8960. Min Act: -0.1700
Data Index: 5034686 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8491. Min Act: -0.1700
Data Index: 7075887 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8491. Min Act: -0.1700
Data Index: 6394496 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8335. Min Act: -0.1700
Data Index: 3321769 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8647. Min Act: -0.1700
Data Index: 372741 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8178. Min Act: -0.1700
Data Index: 7289922 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8178. Min Act: -0.1700
Data Index: 3881735 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.8022. Min Act: -0.1700
Data Index: 641353 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7865. Min Act: -0.1700
Data Index: 530410 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7865. Min Act: -0.1700
Data Index: 8311456 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7865. Min Act: -0.1700
Data Index: 2307870 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7709. Min Act: -0.1700
Data Index: 8539931 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7865. Min Act: -0.1700
Data Index: 3786117 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7865. Min Act: -0.1700
Data Index: 715592 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7709. Min Act: -0.1700
Data Index: 3459540 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7709. Min Act: -0.1700
Data Index: 3088574 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0523. Min Range: -4.0523
Max Act: 3.7553. Min Act: -0.1700
Data Index: 8687736 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19