Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1048. Min Range: -6.1048
Max Act: 6.1048. Min Act: -0.1700
Data Index: 6262358 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.9486. Min Act: -0.1700
Data Index: 775237 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.8861. Min Act: -0.1700
Data Index: 3143213 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.8861. Min Act: -0.1700
Data Index: 8355032 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.8548. Min Act: -0.1700
Data Index: 1648646 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.8548. Min Act: -0.1700
Data Index: 2502785 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.8236. Min Act: -0.1700
Data Index: 2203580 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.7923. Min Act: -0.1700
Data Index: 8578872 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.7923. Min Act: -0.1700
Data Index: 6053175 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.7611. Min Act: -0.1700
Data Index: 8714907 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.7611. Min Act: -0.1700
Data Index: 1060176 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.7298. Min Act: -0.1700
Data Index: 344501 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.7298. Min Act: -0.1700
Data Index: 1131704 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.6986. Min Act: -0.1700
Data Index: 1992948 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 5902197 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.6361. Min Act: -0.1700
Data Index: 8408133 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 6508313 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4453423 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4970776 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1048. Min Range: -6.1048
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3865814 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19