Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3816 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.7879. Min Act: -0.1700
Data Index: 164980 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6941. Min Act: -0.1700
Data Index: 1842855 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6629. Min Act: -0.1700
Data Index: 1440961 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6629. Min Act: -0.1700
Data Index: 5912974 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6316. Min Act: -0.1700
Data Index: 7783122 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6316. Min Act: -0.1700
Data Index: 6619487 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6316. Min Act: -0.1700
Data Index: 7848922 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6316. Min Act: -0.1700
Data Index: 2544925 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6004. Min Act: -0.1700
Data Index: 7668509 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6004. Min Act: -0.1700
Data Index: 4360396 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6004. Min Act: -0.1700
Data Index: 6898422 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6004. Min Act: -0.1700
Data Index: 4148875 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6004. Min Act: -0.1700
Data Index: 6130568 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.5691. Min Act: -0.1700
Data Index: 7487471 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.6004. Min Act: -0.1700
Data Index: 8208033 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.5691. Min Act: -0.1700
Data Index: 3025717 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.5691. Min Act: -0.1700
Data Index: 476569 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.5379. Min Act: -0.1700
Data Index: 4169413 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.5066. Min Act: -0.1700
Data Index: 90495 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7879. Min Range: -6.7879
Max Act: 6.5691. Min Act: -0.1700
Data Index: 6331077 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19