Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5376 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.9977. Min Act: -0.1700
Data Index: 2005154 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.9040. Min Act: -0.1700
Data Index: 8087918 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.8415. Min Act: -0.1700
Data Index: 7090804 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.8727. Min Act: -0.1700
Data Index: 1648758 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.8415. Min Act: -0.1700
Data Index: 5192585 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.7790. Min Act: -0.1700
Data Index: 3747967 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.7477. Min Act: -0.1700
Data Index: 6660787 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.7165. Min Act: -0.1700
Data Index: 5023685 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.6852. Min Act: -0.1700
Data Index: 4337858 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.6540. Min Act: -0.1700
Data Index: 410706 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.6227. Min Act: -0.1700
Data Index: 8751777 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.6227. Min Act: -0.1700
Data Index: 1656245 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.5915. Min Act: -0.1700
Data Index: 6042039 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.5602. Min Act: -0.1700
Data Index: 6371284 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.6227. Min Act: -0.1700
Data Index: 4660820 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.5602. Min Act: -0.1700
Data Index: 431718 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.5602. Min Act: -0.1700
Data Index: 3846800 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.5602. Min Act: -0.1700
Data Index: 6811773 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.5602. Min Act: -0.1700
Data Index: 5755033 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9977. Min Range: -6.9977
Max Act: 6.5602. Min Act: -0.1700
Data Index: 1641002 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19