Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1110. Min Range: -5.1110
Max Act: 5.1110. Min Act: -0.1700
Data Index: 6339413 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1110. Min Range: -5.1110
Max Act: 5.0173. Min Act: -0.1700
Data Index: 693507 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.9860. Min Act: -0.1700
Data Index: 5701764 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.9235. Min Act: -0.1700
Data Index: 72305 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.8610. Min Act: -0.1700
Data Index: 7606616 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.8298. Min Act: -0.1700
Data Index: 7750434 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7985. Min Act: -0.1700
Data Index: 6277397 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7985. Min Act: -0.1700
Data Index: 5917492 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.8298. Min Act: -0.1700
Data Index: 8797810 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7985. Min Act: -0.1700
Data Index: 7024273 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7985. Min Act: -0.1700
Data Index: 6023224 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7673. Min Act: -0.1700
Data Index: 6214432 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7673. Min Act: -0.1700
Data Index: 7205433 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7673. Min Act: -0.1700
Data Index: 1529904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7673. Min Act: -0.1700
Data Index: 4631598 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7673. Min Act: -0.1700
Data Index: 3378262 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7360. Min Act: -0.1700
Data Index: 5685234 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7048. Min Act: -0.1700
Data Index: 4063350 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7360. Min Act: -0.1700
Data Index: 6373771 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1110. Min Range: -5.1110
Max Act: 4.7673. Min Act: -0.1700
Data Index: 7179146 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19