Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.9536. Min Act: -0.1700
Data Index: 302987 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.8911. Min Act: -0.1700
Data Index: 5736542 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.8911. Min Act: -0.1700
Data Index: 2767837 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.8599. Min Act: -0.1700
Data Index: 4949929 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.8286. Min Act: -0.1700
Data Index: 2209299 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7974. Min Act: -0.1700
Data Index: 7795043 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7661. Min Act: -0.1700
Data Index: 188441 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7661. Min Act: -0.1700
Data Index: 7119898 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7349. Min Act: -0.1700
Data Index: 7469461 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7349. Min Act: -0.1700
Data Index: 5777166 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7349. Min Act: -0.1700
Data Index: 8267246 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7661. Min Act: -0.1700
Data Index: 1824930 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7349. Min Act: -0.1700
Data Index: 7307357 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7349. Min Act: -0.1700
Data Index: 8336299 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7036. Min Act: -0.1700
Data Index: 8263690 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7036. Min Act: -0.1700
Data Index: 7841982 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7349. Min Act: -0.1700
Data Index: 4141764 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.6724. Min Act: -0.1700
Data Index: 5078622 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.7036. Min Act: -0.1700
Data Index: 7040230 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9536. Min Range: -5.9536
Max Act: 5.6724. Min Act: -0.1700
Data Index: 1749069 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19