Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.8028. Min Act: -0.1700
Data Index: 1285116 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.6466. Min Act: -0.1700
Data Index: 2830833 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.6153. Min Act: -0.1700
Data Index: 7410379 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.5841. Min Act: -0.1700
Data Index: 1886196 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.5841. Min Act: -0.1700
Data Index: 6589697 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.5216. Min Act: -0.1700
Data Index: 8085528 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.4903. Min Act: -0.1700
Data Index: 1643889 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.4278. Min Act: -0.1700
Data Index: 6740640 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.4591. Min Act: -0.1700
Data Index: 7398475 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3966. Min Act: -0.1700
Data Index: 4901495 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.4278. Min Act: -0.1700
Data Index: 118254 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3966. Min Act: -0.1700
Data Index: 4781144 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3966. Min Act: -0.1700
Data Index: 4456138 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3653. Min Act: -0.1700
Data Index: 7967862 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3653. Min Act: -0.1700
Data Index: 7822998 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3966. Min Act: -0.1700
Data Index: 7585134 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3653. Min Act: -0.1700
Data Index: 5365911 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3653. Min Act: -0.1700
Data Index: 5349183 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3653. Min Act: -0.1700
Data Index: 5217159 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8028. Min Range: -4.8028
Max Act: 4.3653. Min Act: -0.1700
Data Index: 5092100 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19