Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1681. Min Range: -7.1681
Max Act: 7.1681. Min Act: -0.1700
Data Index: 6323427 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1681. Min Range: -7.1681
Max Act: 7.1056. Min Act: -0.1700
Data Index: 6113189 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.9806. Min Act: -0.1700
Data Index: 205246 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.9806. Min Act: -0.1700
Data Index: 7928591 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.9493. Min Act: -0.1700
Data Index: 3371922 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.8868. Min Act: -0.1700
Data Index: 3416883 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.8556. Min Act: -0.1700
Data Index: 563629 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7931. Min Act: -0.1700
Data Index: 8826774 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7618. Min Act: -0.1700
Data Index: 7715705 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7618. Min Act: -0.1700
Data Index: 1502308 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7306. Min Act: -0.1700
Data Index: 702214 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7618. Min Act: -0.1700
Data Index: 2398656 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6993. Min Act: -0.1700
Data Index: 2921078 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6993. Min Act: -0.1700
Data Index: 87624 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6993. Min Act: -0.1700
Data Index: 2706766 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6056. Min Act: -0.1700
Data Index: 702217 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.5743. Min Act: -0.1700
Data Index: 702213 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6056. Min Act: -0.1699
Data Index: 702212 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.5431. Min Act: -0.1700
Data Index: 702211 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.5118. Min Act: -0.1700
Data Index: 702210 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19