Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.9121. Min Act: -0.1700
Data Index: 2374526 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.8183. Min Act: -0.1700
Data Index: 6789503 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.6933. Min Act: -0.1700
Data Index: 4077863 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.5683. Min Act: -0.1700
Data Index: 2956239 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.5996. Min Act: -0.1700
Data Index: 6666601 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.5371. Min Act: -0.1700
Data Index: 4327797 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.5058. Min Act: -0.1700
Data Index: 3312171 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.4746. Min Act: -0.1700
Data Index: 8414646 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.4433. Min Act: -0.1700
Data Index: 6932659 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.4121. Min Act: -0.1700
Data Index: 709815 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.3183. Min Act: -0.1700
Data Index: 8715387 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.3183. Min Act: -0.1700
Data Index: 468443 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.2871. Min Act: -0.1700
Data Index: 1881078 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.3183. Min Act: -0.1700
Data Index: 6248857 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.2871. Min Act: -0.1700
Data Index: 5110343 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.2871. Min Act: -0.1700
Data Index: 835669 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.2558. Min Act: -0.1700
Data Index: 7223385 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.2558. Min Act: -0.1700
Data Index: 3444396 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.2246. Min Act: -0.1700
Data Index: 3728283 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9121. Min Range: -7.9121
Max Act: 7.2558. Min Act: -0.1700
Data Index: 1291132 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19