Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.8919. Min Act: -0.1700
Data Index: 6511835 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.8607. Min Act: -0.1700
Data Index: 4995235 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.8607. Min Act: -0.1700
Data Index: 2122510 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.8294. Min Act: -0.1700
Data Index: 1193317 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.8294. Min Act: -0.1700
Data Index: 659458 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.8294. Min Act: -0.1700
Data Index: 5142490 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7982. Min Act: -0.1700
Data Index: 96529 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7982. Min Act: -0.1700
Data Index: 1677074 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.8294. Min Act: -0.1700
Data Index: 4898906 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7982. Min Act: -0.1700
Data Index: 3624583 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7669. Min Act: -0.1700
Data Index: 1269731 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7357. Min Act: -0.1700
Data Index: 7996223 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7669. Min Act: -0.1700
Data Index: 6855807 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7669. Min Act: -0.1700
Data Index: 5888914 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7357. Min Act: -0.1700
Data Index: 599855 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7357. Min Act: -0.1700
Data Index: 5516686 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7044. Min Act: -0.1700
Data Index: 2008990 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.6732. Min Act: -0.1700
Data Index: 1429370 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7357. Min Act: -0.1700
Data Index: 2864881 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8919. Min Range: -4.8919
Max Act: 4.7044. Min Act: -0.1700
Data Index: 3276101 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19