Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.4255. Min Act: -0.1700
Data Index: 6381015 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.2380. Min Act: -0.1700
Data Index: 5501563 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.1755. Min Act: -0.1700
Data Index: 4772088 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.1130. Min Act: -0.1700
Data Index: 3784026 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.1130. Min Act: -0.1700
Data Index: 842419 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.0505. Min Act: -0.1700
Data Index: 2622984 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.0505. Min Act: -0.1700
Data Index: 5006404 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.0505. Min Act: -0.1700
Data Index: 4805327 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.0505. Min Act: -0.1700
Data Index: 5433842 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.1130. Min Act: -0.1700
Data Index: 3562692 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.1130. Min Act: -0.1700
Data Index: 7667029 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4255. Min Range: -9.4255
Max Act: 9.0505. Min Act: -0.1700
Data Index: 8532903 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9880. Min Act: -0.1700
Data Index: 3562694 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9880. Min Act: -0.1700
Data Index: 2713278 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9880. Min Act: -0.1700
Data Index: 2456392 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9880. Min Act: -0.1700
Data Index: 1102312 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9880. Min Act: -0.1700
Data Index: 7555734 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9880. Min Act: -0.1700
Data Index: 7947193 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9255. Min Act: -0.1700
Data Index: 216902 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4255. Min Range: -9.4255
Max Act: 8.9255. Min Act: -0.1700
Data Index: 6354873 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19