Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.3599. Min Act: -0.1700
Data Index: 7867834 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.3286. Min Act: -0.1700
Data Index: 257848 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2974. Min Act: -0.1700
Data Index: 4985378 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2974. Min Act: -0.1700
Data Index: 587918 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2661. Min Act: -0.1700
Data Index: 2094260 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2661. Min Act: -0.1700
Data Index: 5884380 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2661. Min Act: -0.1700
Data Index: 4177226 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2661. Min Act: -0.1700
Data Index: 3248186 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2349. Min Act: -0.1700
Data Index: 8281057 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2349. Min Act: -0.1700
Data Index: 1493677 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2349. Min Act: -0.1700
Data Index: 1493678 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2349. Min Act: -0.1700
Data Index: 7929850 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2036. Min Act: -0.1700
Data Index: 2081052 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.1724. Min Act: -0.1700
Data Index: 1850508 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2036. Min Act: -0.1700
Data Index: 7648129 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2036. Min Act: -0.1700
Data Index: 4985369 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2036. Min Act: -0.1700
Data Index: 5531714 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.2349. Min Act: -0.1700
Data Index: 4985380 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.1724. Min Act: -0.1700
Data Index: 6759986 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3599. Min Range: -6.3599
Max Act: 6.1724. Min Act: -0.1700
Data Index: 6784335 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19