Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4975 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.7923. Min Act: -0.1700
Data Index: 6203017 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6361. Min Act: -0.1700
Data Index: 4476456 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6048. Min Act: -0.1700
Data Index: 6566135 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6048. Min Act: -0.1700
Data Index: 2162314 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.5423. Min Act: -0.1700
Data Index: 2839493 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.4173. Min Act: -0.1700
Data Index: 5095385 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3861. Min Act: -0.1700
Data Index: 5614598 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.4173. Min Act: -0.1700
Data Index: 8168383 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3548. Min Act: -0.1700
Data Index: 3496826 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3548. Min Act: -0.1700
Data Index: 6330700 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3548. Min Act: -0.1700
Data Index: 7399507 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3548. Min Act: -0.1700
Data Index: 8027649 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3236. Min Act: -0.1700
Data Index: 2769067 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2923. Min Act: -0.1700
Data Index: 4348028 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2611. Min Act: -0.1700
Data Index: 2538821 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2923. Min Act: -0.1700
Data Index: 4179829 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2923. Min Act: -0.1700
Data Index: 3066819 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2923. Min Act: -0.1700
Data Index: 4118985 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6449305 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2611. Min Act: -0.1700
Data Index: 3922442 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19