Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3144 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 21.2389. Min Range: -21.2389
Max Act: 21.2389. Min Act: -0.1700
Data Index: 5416701 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1697
Data Index: 3386050 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1700
Data Index: 703310 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.8639. Min Act: -0.1700
Data Index: 4687097 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1694
Data Index: 1955479 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1700
Data Index: 549659 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1700
Data Index: 6275295 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1648
Data Index: 3951596 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1700
Data Index: 7355511 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.7389. Min Act: -0.1700
Data Index: 2461419 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.7389. Min Act: -0.1700
Data Index: 3748431 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.8639. Min Act: -0.1700
Data Index: 2189493 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.8639. Min Act: -0.1677
Data Index: 2477920 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.8639. Min Act: -0.1700
Data Index: 5335311 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.8639. Min Act: -0.1697
Data Index: 2936964 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.7389. Min Act: -0.1700
Data Index: 3372406 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.8639. Min Act: -0.1697
Data Index: 1818948 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1700
Data Index: 265311 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.9889. Min Act: -0.1699
Data Index: 5684196 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.2389. Min Range: -21.2389
Max Act: 20.8639. Min Act: -0.1700
Data Index: 5930847 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19