Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.2768. Min Act: -0.1700
Data Index: 327583 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1775. Min Act: -0.1700
Data Index: 241689 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1775. Min Act: -0.1700
Data Index: 5507312 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1609. Min Act: -0.1700
Data Index: 4912701 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1442. Min Act: -0.1700
Data Index: 4129479 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1275. Min Act: -0.1700
Data Index: 538947 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1275. Min Act: -0.1700
Data Index: 4717419 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1275. Min Act: -0.1700
Data Index: 4802100 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1108. Min Act: -0.1700
Data Index: 7412863 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1275. Min Act: -0.1700
Data Index: 6061407 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1108. Min Act: -0.1700
Data Index: 6278842 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1108. Min Act: -0.1700
Data Index: 4728042 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1108. Min Act: -0.1700
Data Index: 7551050 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1108. Min Act: -0.1700
Data Index: 4999137 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.0941. Min Act: -0.1700
Data Index: 6124483 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.0941. Min Act: -0.1700
Data Index: 4777873 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.1108. Min Act: -0.1700
Data Index: 2730590 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.0773. Min Act: -0.1700
Data Index: 3013848 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.0941. Min Act: -0.1700
Data Index: 5952874 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2768. Min Range: -2.2768
Max Act: 2.0941. Min Act: -0.1700
Data Index: 1325944 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19