Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.9848. Min Act: -0.1700
Data Index: 8294897 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7973. Min Act: -0.1700
Data Index: 1586642 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7973. Min Act: -0.1700
Data Index: 489473 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7660. Min Act: -0.1700
Data Index: 8642306 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7660. Min Act: -0.1700
Data Index: 4700961 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7660. Min Act: -0.1700
Data Index: 6451666 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7660. Min Act: -0.1700
Data Index: 7098246 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7660. Min Act: -0.1700
Data Index: 6177358 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7348. Min Act: -0.1700
Data Index: 2585851 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7348. Min Act: -0.1700
Data Index: 3396969 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7348. Min Act: -0.1700
Data Index: 711038 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 6839044 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 213282 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 6967056 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 2526991 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.7035. Min Act: -0.1700
Data Index: 2115894 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6723. Min Act: -0.1700
Data Index: 8137812 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6723. Min Act: -0.1700
Data Index: 2585850 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6723. Min Act: -0.1700
Data Index: 1525179 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9848. Min Range: -5.9848
Max Act: 5.6723. Min Act: -0.1700
Data Index: 4807647 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19