Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2088 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.9614. Min Act: -0.1700
Data Index: 7390700 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.9301. Min Act: -0.1700
Data Index: 5699332 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.8676. Min Act: -0.1700
Data Index: 6364367 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.8363. Min Act: -0.1700
Data Index: 772534 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.8363. Min Act: -0.1700
Data Index: 6842185 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.7425. Min Act: -0.1700
Data Index: 2325877 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.7425. Min Act: -0.1700
Data Index: 2028649 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.7112. Min Act: -0.1700
Data Index: 4680888 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.7112. Min Act: -0.1700
Data Index: 427550 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.7112. Min Act: -0.1700
Data Index: 2927024 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.7112. Min Act: -0.1700
Data Index: 1628174 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6799. Min Act: -0.1700
Data Index: 2526626 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6799. Min Act: -0.1700
Data Index: 2061903 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6799. Min Act: -0.1700
Data Index: 8623220 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6799. Min Act: -0.1700
Data Index: 1296886 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6486. Min Act: -0.1700
Data Index: 4815572 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6486. Min Act: -0.1700
Data Index: 4503922 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6486. Min Act: -0.1700
Data Index: 8307955 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6799. Min Act: -0.1700
Data Index: 3520107 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9614. Min Range: -3.9614
Max Act: 3.6486. Min Act: -0.1700
Data Index: 3988179 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19