Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.7379. Min Act: -0.1700
Data Index: 7586162 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.7379. Min Act: -0.1700
Data Index: 7521515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.7067. Min Act: -0.1700
Data Index: 7822322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.7067. Min Act: -0.1700
Data Index: 2098349 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.7067. Min Act: -0.1700
Data Index: 8616267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6754. Min Act: -0.1698
Data Index: 8481532 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6754. Min Act: -0.1700
Data Index: 4177766 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6754. Min Act: -0.1700
Data Index: 2394486 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 7513864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 4018045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 76700 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 306603 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 7147762 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 4016913 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 80982 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 6907371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6128. Min Act: -0.1700
Data Index: 6696188 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 6184270 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 3745876 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7379. Min Range: -3.7379
Max Act: 3.6441. Min Act: -0.1700
Data Index: 3510448 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19