Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1024. Min Range: -6.1024
Max Act: 6.1024. Min Act: -0.1700
Data Index: 8320477 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1024. Min Range: -6.1024
Max Act: 6.0711. Min Act: -0.1700
Data Index: 951698 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1024. Min Range: -6.1024
Max Act: 6.0711. Min Act: -0.1700
Data Index: 4071909 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.9774. Min Act: -0.1700
Data Index: 5323722 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1024. Min Range: -6.1024
Max Act: 6.0086. Min Act: -0.1700
Data Index: 951697 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1024. Min Range: -6.1024
Max Act: 6.0086. Min Act: -0.1700
Data Index: 951699 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.9149. Min Act: -0.1700
Data Index: 3264438 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.9149. Min Act: -0.1700
Data Index: 5971619 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.9149. Min Act: -0.1700
Data Index: 6452664 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.9149. Min Act: -0.1700
Data Index: 52483 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.9149. Min Act: -0.1700
Data Index: 4211785 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.9149. Min Act: -0.1700
Data Index: 3589166 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8836. Min Act: -0.1700
Data Index: 951700 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8836. Min Act: -0.1700
Data Index: 2920366 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8524. Min Act: -0.1700
Data Index: 3565891 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8524. Min Act: -0.1700
Data Index: 5230560 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8836. Min Act: -0.1700
Data Index: 2179102 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8836. Min Act: -0.1700
Data Index: 4877451 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8524. Min Act: -0.1700
Data Index: 301031 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1024. Min Range: -6.1024
Max Act: 5.8211. Min Act: -0.1700
Data Index: 5418971 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19