Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1212 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.5833. Min Act: -0.1700
Data Index: 3086486 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.5833. Min Act: -0.1700
Data Index: 4605353 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.4583. Min Act: -0.1700
Data Index: 817502 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.3958. Min Act: -0.1700
Data Index: 3062363 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.3958. Min Act: -0.1700
Data Index: 5165287 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.2708. Min Act: -0.1700
Data Index: 1560419 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.2083. Min Act: -0.1700
Data Index: 206005 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.2083. Min Act: -0.1700
Data Index: 650848 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.2083. Min Act: -0.1700
Data Index: 6108743 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.2083. Min Act: -0.1700
Data Index: 5369887 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.1458. Min Act: -0.1700
Data Index: 6700594 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.1458. Min Act: -0.1700
Data Index: 1305812 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.1458. Min Act: -0.1700
Data Index: 10656 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.0833. Min Act: -0.1700
Data Index: 4342923 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.0833. Min Act: -0.1700
Data Index: 3334478 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.0208. Min Act: -0.1700
Data Index: 52414 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.0208. Min Act: -0.1700
Data Index: 1405441 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5833. Min Range: -9.5833
Max Act: 9.0208. Min Act: -0.1700
Data Index: 5861573 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5833. Min Range: -9.5833
Max Act: 8.9583. Min Act: -0.1700
Data Index: 3373007 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5833. Min Range: -9.5833
Max Act: 8.9583. Min Act: -0.1700
Data Index: 5648110 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19