Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2063 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4992. Min Range: -7.4992
Max Act: 7.4992. Min Act: -0.1700
Data Index: 6948885 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4992. Min Range: -7.4992
Max Act: 7.2492. Min Act: -0.1700
Data Index: 165641 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4992. Min Range: -7.4992
Max Act: 7.2180. Min Act: -0.1700
Data Index: 4857202 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4992. Min Range: -7.4992
Max Act: 7.0617. Min Act: -0.1700
Data Index: 6924846 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4992. Min Range: -7.4992
Max Act: 7.0617. Min Act: -0.1700
Data Index: 7788655 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.9992. Min Act: -0.1700
Data Index: 7538579 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.9680. Min Act: -0.1700
Data Index: 7635258 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.9367. Min Act: -0.1700
Data Index: 3246657 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.9367. Min Act: -0.1700
Data Index: 79109 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.8430. Min Act: -0.1700
Data Index: 4408432 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.8742. Min Act: -0.1700
Data Index: 2356888 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.8430. Min Act: -0.1700
Data Index: 5858316 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.8430. Min Act: -0.1700
Data Index: 6925610 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.8117. Min Act: -0.1700
Data Index: 141112 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.8117. Min Act: -0.1700
Data Index: 3999423 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.7805. Min Act: -0.1700
Data Index: 5099608 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.7805. Min Act: -0.1700
Data Index: 3749000 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.7805. Min Act: -0.1700
Data Index: 4049002 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.7180. Min Act: -0.1700
Data Index: 2213545 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4992. Min Range: -7.4992
Max Act: 6.6867. Min Act: -0.1700
Data Index: 5801720 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19