Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.6469. Min Act: -0.1700
Data Index: 3836724 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.5219. Min Act: -0.1700
Data Index: 3637824 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.5219. Min Act: -0.1700
Data Index: 820499 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.5219. Min Act: -0.1700
Data Index: 7229190 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.4282. Min Act: -0.1700
Data Index: 2219602 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3969. Min Act: -0.1700
Data Index: 5422529 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3344. Min Act: -0.1700
Data Index: 6566798 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3344. Min Act: -0.1700
Data Index: 3657795 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3344. Min Act: -0.1700
Data Index: 5176723 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3344. Min Act: -0.1700
Data Index: 2213620 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3344. Min Act: -0.1700
Data Index: 2158888 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3032. Min Act: -0.1700
Data Index: 8025676 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.3032. Min Act: -0.1700
Data Index: 3474470 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.2719. Min Act: -0.1700
Data Index: 5964959 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.2719. Min Act: -0.1700
Data Index: 5627744 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.2719. Min Act: -0.1700
Data Index: 8077478 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.2407. Min Act: -0.1700
Data Index: 6833760 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.2407. Min Act: -0.1700
Data Index: 3350009 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.2094. Min Act: -0.1700
Data Index: 7931999 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6469. Min Range: -6.6469
Max Act: 6.2407. Min Act: -0.1700
Data Index: 3818347 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19