Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.7856. Min Act: -0.1700
Data Index: 8360646 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6918. Min Act: -0.1700
Data Index: 7715471 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6918. Min Act: -0.1700
Data Index: 4243034 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6292. Min Act: -0.1700
Data Index: 3233841 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6605. Min Act: -0.1700
Data Index: 740505 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6605. Min Act: -0.1700
Data Index: 1511468 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6292. Min Act: -0.1700
Data Index: 2008244 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5822. Min Act: -0.1700
Data Index: 2338119 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5979. Min Act: -0.1700
Data Index: 6854866 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.6135. Min Act: -0.1700
Data Index: 5282656 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5822. Min Act: -0.1700
Data Index: 740506 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5666. Min Act: -0.1700
Data Index: 7360241 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5666. Min Act: -0.1700
Data Index: 7489872 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5666. Min Act: -0.1700
Data Index: 4434523 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5353. Min Act: -0.1700
Data Index: 5464535 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5353. Min Act: -0.1700
Data Index: 3429972 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5353. Min Act: -0.1700
Data Index: 7211549 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5353. Min Act: -0.1700
Data Index: 5911663 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5196. Min Act: -0.1700
Data Index: 6296704 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7856. Min Range: -3.7856
Max Act: 3.5353. Min Act: -0.1700
Data Index: 1932260 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19