Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.6378. Min Act: -0.1700
Data Index: 3601328 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.4815. Min Act: -0.1700
Data Index: 1401480 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.3565. Min Act: -0.1700
Data Index: 975645 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.2940. Min Act: -0.1700
Data Index: 7179867 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.3253. Min Act: -0.1700
Data Index: 8735685 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.2315. Min Act: -0.1700
Data Index: 7089706 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.2315. Min Act: -0.1700
Data Index: 7639867 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.2003. Min Act: -0.1700
Data Index: 2074388 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.2003. Min Act: -0.1700
Data Index: 7967213 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.2003. Min Act: -0.1700
Data Index: 2524810 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1690. Min Act: -0.1700
Data Index: 4058000 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1690. Min Act: -0.1700
Data Index: 1125852 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.2003. Min Act: -0.1700
Data Index: 4611646 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1690. Min Act: -0.1700
Data Index: 507224 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1378. Min Act: -0.1700
Data Index: 8114608 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1378. Min Act: -0.1700
Data Index: 6384962 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1378. Min Act: -0.1700
Data Index: 5856254 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1065. Min Act: -0.1700
Data Index: 2946696 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.1378. Min Act: -0.1700
Data Index: 4526053 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6378. Min Range: -7.6378
Max Act: 7.0753. Min Act: -0.1700
Data Index: 6763665 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19