Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.6493. Min Act: -0.1700
Data Index: 6795395 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.6806. Min Act: -0.1700
Data Index: 1691663 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.5243. Min Act: -0.1700
Data Index: 6267511 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.5243. Min Act: -0.1700
Data Index: 6918798 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4931. Min Act: -0.1700
Data Index: 2161690 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4931. Min Act: -0.1700
Data Index: 6578903 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4931. Min Act: -0.1700
Data Index: 2052829 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4931. Min Act: -0.1700
Data Index: 6589588 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4931. Min Act: -0.1700
Data Index: 2263422 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4618. Min Act: -0.1700
Data Index: 4659501 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4618. Min Act: -0.1700
Data Index: 1200487 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 1609803 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 1928783 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 102044 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 4060098 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 8560992 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 7353526 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 7650410 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.4306. Min Act: -0.1700
Data Index: 8168446 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6806. Min Range: -4.6806
Max Act: 4.3993. Min Act: -0.1700
Data Index: 8032800 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19