Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1991. Min Range: -6.1991
Max Act: 6.1991. Min Act: -0.1700
Data Index: 2307767 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1991. Min Range: -6.1991
Max Act: 6.0741. Min Act: -0.1700
Data Index: 41871 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.9803. Min Act: -0.1700
Data Index: 2680779 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.9178. Min Act: -0.1700
Data Index: 6194910 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.9178. Min Act: -0.1700
Data Index: 7364749 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8866. Min Act: -0.1700
Data Index: 5594153 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8866. Min Act: -0.1700
Data Index: 856199 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8866. Min Act: -0.1700
Data Index: 2145014 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8866. Min Act: -0.1700
Data Index: 8097684 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8866. Min Act: -0.1700
Data Index: 7962762 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8553. Min Act: -0.1700
Data Index: 6969873 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8241. Min Act: -0.1700
Data Index: 5666934 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.8241. Min Act: -0.1700
Data Index: 4415370 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.7928. Min Act: -0.1700
Data Index: 3083146 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.7928. Min Act: -0.1700
Data Index: 2431421 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.7616. Min Act: -0.1700
Data Index: 1972961 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.7928. Min Act: -0.1700
Data Index: 640845 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.7928. Min Act: -0.1700
Data Index: 3265999 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.7616. Min Act: -0.1700
Data Index: 2398529 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1991. Min Range: -6.1991
Max Act: 5.7303. Min Act: -0.1700
Data Index: 3149298 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19