Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5538 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1242. Min Range: -6.1242
Max Act: 6.1242. Min Act: -0.1700
Data Index: 8115586 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.9679. Min Act: -0.1700
Data Index: 1785771 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.9367. Min Act: -0.1700
Data Index: 3144704 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.8429. Min Act: -0.1700
Data Index: 6962968 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.8117. Min Act: -0.1700
Data Index: 7035687 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.7804. Min Act: -0.1700
Data Index: 2006377 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.7804. Min Act: -0.1700
Data Index: 13068 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.7492. Min Act: -0.1700
Data Index: 7378692 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.7492. Min Act: -0.1700
Data Index: 6367922 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.7179. Min Act: -0.1700
Data Index: 8133468 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.7179. Min Act: -0.1700
Data Index: 4351471 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.6554. Min Act: -0.1700
Data Index: 5463646 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.6242. Min Act: -0.1700
Data Index: 7169360 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.5929. Min Act: -0.1700
Data Index: 1483559 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.5929. Min Act: -0.1700
Data Index: 3699657 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.5929. Min Act: -0.1700
Data Index: 6305037 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.5617. Min Act: -0.1700
Data Index: 476900 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.5929. Min Act: -0.1700
Data Index: 4205927 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.5617. Min Act: -0.1700
Data Index: 4318960 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1242. Min Range: -6.1242
Max Act: 5.5617. Min Act: -0.1700
Data Index: 8030610 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19