Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1704. Min Range: -9.1704
Max Act: 9.1704. Min Act: -0.1700
Data Index: 2144021 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1704. Min Range: -9.1704
Max Act: 9.0454. Min Act: -0.1700
Data Index: 922938 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.9204. Min Act: -0.1700
Data Index: 7098718 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.8579. Min Act: -0.1700
Data Index: 1095730 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.7954. Min Act: -0.1700
Data Index: 5346514 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.6704. Min Act: -0.1700
Data Index: 2748867 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.6079. Min Act: -0.1700
Data Index: 6660013 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.6079. Min Act: -0.1700
Data Index: 4830177 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.5454. Min Act: -0.1700
Data Index: 7974948 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.6079. Min Act: -0.1700
Data Index: 2036681 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4829. Min Act: -0.1700
Data Index: 5561469 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4829. Min Act: -0.1700
Data Index: 86595 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4829. Min Act: -0.1700
Data Index: 6380703 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.3579. Min Act: -0.1700
Data Index: 3729190 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4204. Min Act: -0.1700
Data Index: 3159869 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4204. Min Act: -0.1700
Data Index: 5875420 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4204. Min Act: -0.1700
Data Index: 2011257 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4204. Min Act: -0.1700
Data Index: 4322345 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.4204. Min Act: -0.1700
Data Index: 4580697 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1704. Min Range: -9.1704
Max Act: 8.3579. Min Act: -0.1700
Data Index: 4490148 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19