Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1923 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5826. Min Range: -6.5826
Max Act: 6.5826. Min Act: -0.1700
Data Index: 4066413 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5826. Min Range: -6.5826
Max Act: 6.3326. Min Act: -0.1700
Data Index: 2989399 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5826. Min Range: -6.5826
Max Act: 6.2076. Min Act: -0.1700
Data Index: 7434075 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5826. Min Range: -6.5826
Max Act: 6.1451. Min Act: -0.1700
Data Index: 5594571 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5826. Min Range: -6.5826
Max Act: 6.0826. Min Act: -0.1700
Data Index: 7968640 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5826. Min Range: -6.5826
Max Act: 6.0826. Min Act: -0.1700
Data Index: 587263 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5826. Min Range: -6.5826
Max Act: 6.0201. Min Act: -0.1700
Data Index: 2024713 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.9576. Min Act: -0.1700
Data Index: 1265080 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.9264. Min Act: -0.1700
Data Index: 5040622 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.9576. Min Act: -0.1700
Data Index: 5751984 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.9576. Min Act: -0.1700
Data Index: 6737423 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.9264. Min Act: -0.1700
Data Index: 831650 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.9264. Min Act: -0.1700
Data Index: 5635882 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.8639. Min Act: -0.1700
Data Index: 6320567 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.8326. Min Act: -0.1700
Data Index: 2326953 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.7701. Min Act: -0.1700
Data Index: 5306240 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.7701. Min Act: -0.1700
Data Index: 3063892 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.7389. Min Act: -0.1700
Data Index: 6392098 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.7701. Min Act: -0.1700
Data Index: 237113 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5826. Min Range: -6.5826
Max Act: 5.7389. Min Act: -0.1700
Data Index: 4887784 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19