Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.7396. Min Act: -0.1700
Data Index: 1632672 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.6771. Min Act: -0.1700
Data Index: 7340182 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.6146. Min Act: -0.1700
Data Index: 6356865 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.6146. Min Act: -0.1700
Data Index: 138240 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5833. Min Act: -0.1700
Data Index: 4157952 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5521. Min Act: -0.1700
Data Index: 2081954 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5521. Min Act: -0.1700
Data Index: 7807533 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5208. Min Act: -0.1700
Data Index: 7641828 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5208. Min Act: -0.1700
Data Index: 6886705 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5208. Min Act: -0.1700
Data Index: 1824299 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5208. Min Act: -0.1700
Data Index: 1605791 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.5208. Min Act: -0.1700
Data Index: 7903892 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4583. Min Act: -0.1700
Data Index: 808062 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4896. Min Act: -0.1700
Data Index: 2651460 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4896. Min Act: -0.1700
Data Index: 7475763 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4896. Min Act: -0.1700
Data Index: 772171 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4583. Min Act: -0.1700
Data Index: 2050499 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4583. Min Act: -0.1700
Data Index: 1162182 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4583. Min Act: -0.1700
Data Index: 7640979 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7396. Min Range: -5.7396
Max Act: 5.4583. Min Act: -0.1700
Data Index: 51592 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19