Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.6188. Min Act: -0.1700
Data Index: 2890426 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.4626. Min Act: -0.1700
Data Index: 182940 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.2751. Min Act: -0.1700
Data Index: 8608263 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.2438. Min Act: -0.1700
Data Index: 3547132 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.2438. Min Act: -0.1700
Data Index: 2468289 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.2126. Min Act: -0.1700
Data Index: 5986540 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.2126. Min Act: -0.1700
Data Index: 1012147 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.1501. Min Act: -0.1700
Data Index: 8733348 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.1813. Min Act: -0.1700
Data Index: 1245036 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.1813. Min Act: -0.1700
Data Index: 463617 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.1501. Min Act: -0.1700
Data Index: 1235623 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.0563. Min Act: -0.1700
Data Index: 8645365 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.0563. Min Act: -0.1700
Data Index: 3538884 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.0563. Min Act: -0.1700
Data Index: 6384773 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.0563. Min Act: -0.1700
Data Index: 1435268 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6188. Min Range: -7.6188
Max Act: 6.9938. Min Act: -0.1700
Data Index: 705813 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6188. Min Range: -7.6188
Max Act: 7.0251. Min Act: -0.1700
Data Index: 2435471 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6188. Min Range: -7.6188
Max Act: 6.9938. Min Act: -0.1700
Data Index: 8498560 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6188. Min Range: -7.6188
Max Act: 6.9938. Min Act: -0.1700
Data Index: 1630966 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6188. Min Range: -7.6188
Max Act: 6.9626. Min Act: -0.1700
Data Index: 7125827 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19