Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5852 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1108. Min Range: -5.1108
Max Act: 5.1108. Min Act: -0.1700
Data Index: 2051825 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.8921. Min Act: -0.1700
Data Index: 4467616 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.8608. Min Act: -0.1700
Data Index: 7572798 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.7983. Min Act: -0.1700
Data Index: 3086526 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.7671. Min Act: -0.1700
Data Index: 1765084 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.7671. Min Act: -0.1700
Data Index: 967977 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.7046. Min Act: -0.1700
Data Index: 1916520 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.7046. Min Act: -0.1700
Data Index: 2315196 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6733. Min Act: -0.1700
Data Index: 3717774 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6733. Min Act: -0.1700
Data Index: 6446130 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6733. Min Act: -0.1700
Data Index: 1954084 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6733. Min Act: -0.1700
Data Index: 1866544 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6421. Min Act: -0.1700
Data Index: 6039338 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6421. Min Act: -0.1700
Data Index: 4840690 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6421. Min Act: -0.1700
Data Index: 2394679 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6108. Min Act: -0.1700
Data Index: 3440154 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6421. Min Act: -0.1700
Data Index: 7093096 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6421. Min Act: -0.1700
Data Index: 1452879 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6421. Min Act: -0.1700
Data Index: 4604500 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1108. Min Range: -5.1108
Max Act: 4.6421. Min Act: -0.1700
Data Index: 4801456 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19