Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.7228. Min Act: -0.1700
Data Index: 1087520 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.5978. Min Act: -0.1700
Data Index: 1022332 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.5978. Min Act: -0.1700
Data Index: 6125720 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.5666. Min Act: -0.1700
Data Index: 1655872 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.5666. Min Act: -0.1700
Data Index: 224686 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.4728. Min Act: -0.1700
Data Index: 5346450 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.4416. Min Act: -0.1700
Data Index: 5383360 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.4103. Min Act: -0.1700
Data Index: 6376800 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.3791. Min Act: -0.1700
Data Index: 7805393 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2853. Min Act: -0.1700
Data Index: 3491457 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2541. Min Act: -0.1700
Data Index: 2741284 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2228. Min Act: -0.1700
Data Index: 2789005 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2228. Min Act: -0.1700
Data Index: 2327556 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2228. Min Act: -0.1700
Data Index: 5867371 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2541. Min Act: -0.1700
Data Index: 1116927 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2544170 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 5832400 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.2228. Min Act: -0.1700
Data Index: 5551905 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 5535024 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7228. Min Range: -6.7228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 2804567 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19