Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.7923. Min Act: -0.1700
Data Index: 1569520 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.6673. Min Act: -0.1700
Data Index: 6061088 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.5111. Min Act: -0.1700
Data Index: 2045863 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.4173. Min Act: -0.1700
Data Index: 8451217 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.4486. Min Act: -0.1700
Data Index: 7134104 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.4798. Min Act: -0.1700
Data Index: 603843 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.4486. Min Act: -0.1700
Data Index: 8620742 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.4173. Min Act: -0.1700
Data Index: 5085742 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.4173. Min Act: -0.1700
Data Index: 1380398 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3861. Min Act: -0.1700
Data Index: 3594447 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3861. Min Act: -0.1700
Data Index: 1773553 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3861. Min Act: -0.1700
Data Index: 5955908 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3548. Min Act: -0.1700
Data Index: 3165866 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3548. Min Act: -0.1700
Data Index: 285859 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3548. Min Act: -0.1700
Data Index: 4052886 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3548. Min Act: -0.1700
Data Index: 633502 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3548. Min Act: -0.1700
Data Index: 7814504 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3548. Min Act: -0.1700
Data Index: 4880608 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3548. Min Act: -0.1700
Data Index: 7259477 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7923. Min Range: -4.7923
Max Act: 4.3236. Min Act: -0.1700
Data Index: 4377630 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19