Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4204. Min Range: -9.4204
Max Act: 9.4204. Min Act: -0.1700
Data Index: 5207469 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4204. Min Range: -9.4204
Max Act: 9.2329. Min Act: -0.1700
Data Index: 3871772 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4204. Min Range: -9.4204
Max Act: 9.1704. Min Act: -0.1700
Data Index: 6547666 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4204. Min Range: -9.4204
Max Act: 9.1079. Min Act: -0.1700
Data Index: 4257958 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4204. Min Range: -9.4204
Max Act: 9.1079. Min Act: -0.1700
Data Index: 1962800 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4204. Min Range: -9.4204
Max Act: 9.1079. Min Act: -0.1700
Data Index: 2258821 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4204. Min Range: -9.4204
Max Act: 9.1079. Min Act: -0.1700
Data Index: 3378902 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9204. Min Act: -0.1700
Data Index: 5605576 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9829. Min Act: -0.1700
Data Index: 5657586 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9829. Min Act: -0.1700
Data Index: 3534014 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9829. Min Act: -0.1700
Data Index: 64037 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9204. Min Act: -0.1700
Data Index: 4568059 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9204. Min Act: -0.1700
Data Index: 7553770 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9204. Min Act: -0.1700
Data Index: 8638518 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9204. Min Act: -0.1700
Data Index: 6021333 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.9204. Min Act: -0.1700
Data Index: 7727594 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.8579. Min Act: -0.1700
Data Index: 3688734 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.8579. Min Act: -0.1700
Data Index: 4278312 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.8579. Min Act: -0.1700
Data Index: 4620341 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4204. Min Range: -9.4204
Max Act: 8.7954. Min Act: -0.1700
Data Index: 6842212 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19