Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.7306. Min Act: -0.1698
Data Index: 2371401 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.3556. Min Act: -0.1683
Data Index: 1527126 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.2931. Min Act: -0.1682
Data Index: 2371412 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.2931. Min Act: -0.1685
Data Index: 4042218 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.2931. Min Act: -0.1697
Data Index: 5660383 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.2306. Min Act: -0.1698
Data Index: 686108 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.2306. Min Act: -0.1700
Data Index: 4042221 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.2931. Min Act: -0.1699
Data Index: 8181626 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.1681. Min Act: -0.1489
Data Index: 7615196 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.1056. Min Act: -0.1685
Data Index: 8181630 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.1056. Min Act: -0.1691
Data Index: 8181643 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.1056. Min Act: -0.1685
Data Index: 8504038 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.1056. Min Act: -0.1663
Data Index: 7970614 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.1056. Min Act: -0.1656
Data Index: 3108585 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.0431. Min Act: -0.1697
Data Index: 2371409 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.0431. Min Act: -0.1697
Data Index: 2680923 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7306. Min Range: -9.7306
Max Act: 8.9806. Min Act: -0.1687
Data Index: 8181621 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.0431. Min Act: -0.1693
Data Index: 13767 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.0431. Min Act: -0.1700
Data Index: 2371396 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7306. Min Range: -9.7306
Max Act: 9.1056. Min Act: -0.1451
Data Index: 2371397 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19