Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0379. Min Range: -8.0379
Max Act: 8.0379. Min Act: -0.1700
Data Index: 7521468 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.9441. Min Act: -0.1700
Data Index: 843805 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.8504. Min Act: -0.1700
Data Index: 5762241 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.7566. Min Act: -0.1700
Data Index: 573899 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.7254. Min Act: -0.1700
Data Index: 1953670 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.6941. Min Act: -0.1700
Data Index: 2837055 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.6004. Min Act: -0.1700
Data Index: 4125683 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.6316. Min Act: -0.1700
Data Index: 6448668 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5691. Min Act: -0.1700
Data Index: 5200656 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.6004. Min Act: -0.1700
Data Index: 7612024 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.6004. Min Act: -0.1700
Data Index: 6466891 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5379. Min Act: -0.1700
Data Index: 1188610 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5691. Min Act: -0.1700
Data Index: 6622364 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5691. Min Act: -0.1700
Data Index: 7987719 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5691. Min Act: -0.1700
Data Index: 435419 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5379. Min Act: -0.1700
Data Index: 8362102 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5379. Min Act: -0.1700
Data Index: 6768046 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5691. Min Act: -0.1700
Data Index: 1453146 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.5066. Min Act: -0.1700
Data Index: 7262949 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0379. Min Range: -8.0379
Max Act: 7.4754. Min Act: -0.1700
Data Index: 443923 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19