Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.6986. Min Act: -0.1700
Data Index: 3409047 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.2611. Min Act: -0.1700
Data Index: 1521757 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.1673. Min Act: -0.1700
Data Index: 595171 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.1673. Min Act: -0.1700
Data Index: 4107772 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.1361. Min Act: -0.1700
Data Index: 5037094 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.1361. Min Act: -0.1700
Data Index: 2971833 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.1048. Min Act: -0.1700
Data Index: 77610 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6986. Min Range: -7.6986
Max Act: 7.1048. Min Act: -0.1700
Data Index: 7966904 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9798. Min Act: -0.1700
Data Index: 649437 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9798. Min Act: -0.1700
Data Index: 323442 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9486. Min Act: -0.1700
Data Index: 6652048 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9173. Min Act: -0.1700
Data Index: 3743492 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9486. Min Act: -0.1700
Data Index: 5087927 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9486. Min Act: -0.1700
Data Index: 5274822 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9486. Min Act: -0.1700
Data Index: 6212668 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9173. Min Act: -0.1700
Data Index: 3519218 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.8861. Min Act: -0.1700
Data Index: 5076170 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9173. Min Act: -0.1700
Data Index: 2970293 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.9173. Min Act: -0.1700
Data Index: 7205031 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6986. Min Range: -7.6986
Max Act: 6.8861. Min Act: -0.1700
Data Index: 7848081 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19