Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6207. Min Range: -7.6207
Max Act: 7.6207. Min Act: -0.1700
Data Index: 2075684 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6207. Min Range: -7.6207
Max Act: 7.3707. Min Act: -0.1700
Data Index: 5100640 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6207. Min Range: -7.6207
Max Act: 7.1832. Min Act: -0.1700
Data Index: 5091203 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6207. Min Range: -7.6207
Max Act: 7.0582. Min Act: -0.1700
Data Index: 6863152 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6207. Min Range: -7.6207
Max Act: 7.0582. Min Act: -0.1700
Data Index: 419727 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.9645. Min Act: -0.1700
Data Index: 8831497 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.9332. Min Act: -0.1700
Data Index: 3437682 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.8082. Min Act: -0.1700
Data Index: 3397088 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.7770. Min Act: -0.1700
Data Index: 4207256 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.7770. Min Act: -0.1700
Data Index: 2624891 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.7457. Min Act: -0.1700
Data Index: 3718048 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.7145. Min Act: -0.1700
Data Index: 2643489 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6520. Min Act: -0.1700
Data Index: 4750066 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6520. Min Act: -0.1700
Data Index: 5547211 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6832. Min Act: -0.1700
Data Index: 2109253 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6520. Min Act: -0.1700
Data Index: 3963426 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6520. Min Act: -0.1700
Data Index: 8571598 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6520. Min Act: -0.1700
Data Index: 8703226 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6520. Min Act: -0.1700
Data Index: 5528986 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6207. Min Range: -7.6207
Max Act: 6.6207. Min Act: -0.1700
Data Index: 2582176 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19