Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1934 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.8713. Min Act: -0.1700
Data Index: 2246509 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.8088. Min Act: -0.1700
Data Index: 122752 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.8088. Min Act: -0.1700
Data Index: 8748684 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.7463. Min Act: -0.1700
Data Index: 2675897 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.6213. Min Act: -0.1700
Data Index: 6569987 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.6213. Min Act: -0.1700
Data Index: 7789395 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3713. Min Act: -0.1700
Data Index: 6172086 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3713. Min Act: -0.1700
Data Index: 7727915 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3088. Min Act: -0.1700
Data Index: 7523004 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3088. Min Act: -0.1700
Data Index: 6067157 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3088. Min Act: -0.1700
Data Index: 871228 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3088. Min Act: -0.1700
Data Index: 3401246 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3088. Min Act: -0.1700
Data Index: 349280 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3713. Min Act: -0.1700
Data Index: 1516088 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3088. Min Act: -0.1700
Data Index: 933976 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.3088. Min Act: -0.1700
Data Index: 2603795 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.2463. Min Act: -0.1700
Data Index: 4209954 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.2463. Min Act: -0.1700
Data Index: 7334837 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.1838. Min Act: -0.1700
Data Index: 3068789 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8713. Min Range: -8.8713
Max Act: 8.2463. Min Act: -0.1700
Data Index: 5579765 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19