Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 197 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2590. Min Range: -6.2590
Max Act: 6.2590. Min Act: -0.1700
Data Index: 1868790 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2590. Min Range: -6.2590
Max Act: 6.1965. Min Act: -0.1700
Data Index: 742861 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.8840. Min Act: -0.1700
Data Index: 5156906 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.8527. Min Act: -0.1700
Data Index: 4318853 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.8215. Min Act: -0.1700
Data Index: 3990345 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.7902. Min Act: -0.1700
Data Index: 4935409 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.7277. Min Act: -0.1700
Data Index: 7382581 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.7590. Min Act: -0.1700
Data Index: 6454146 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.7277. Min Act: -0.1700
Data Index: 819952 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6965. Min Act: -0.1700
Data Index: 3567270 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6652. Min Act: -0.1700
Data Index: 51234 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6652. Min Act: -0.1700
Data Index: 5134691 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6027. Min Act: -0.1700
Data Index: 4800521 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6340. Min Act: -0.1700
Data Index: 7096782 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6340. Min Act: -0.1700
Data Index: 3279122 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6027. Min Act: -0.1700
Data Index: 1810885 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6027. Min Act: -0.1700
Data Index: 5348466 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.6027. Min Act: -0.1700
Data Index: 2665376 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.5715. Min Act: -0.1700
Data Index: 4814140 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2590. Min Range: -6.2590
Max Act: 5.5715. Min Act: -0.1700
Data Index: 7048869 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19