Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4209 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3738. Min Range: -6.3738
Max Act: 6.3738. Min Act: -0.1700
Data Index: 5284332 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3738. Min Range: -6.3738
Max Act: 6.1551. Min Act: -0.1700
Data Index: 5284344 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.9676. Min Act: -0.1700
Data Index: 6475783 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.9676. Min Act: -0.1700
Data Index: 6222310 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.9363. Min Act: -0.1700
Data Index: 6475781 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.9051. Min Act: -0.1700
Data Index: 4536716 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.9051. Min Act: -0.1700
Data Index: 4947861 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.9051. Min Act: -0.1700
Data Index: 4792484 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.8738. Min Act: -0.1700
Data Index: 7453889 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.8426. Min Act: -0.1700
Data Index: 4547395 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.8426. Min Act: -0.1700
Data Index: 5284328 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.8113. Min Act: -0.1700
Data Index: 7453886 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.8113. Min Act: -0.1700
Data Index: 1241712 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.7801. Min Act: -0.1700
Data Index: 3065824 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.7801. Min Act: -0.1700
Data Index: 2656499 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5575962 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.7801. Min Act: -0.1700
Data Index: 8548907 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.7488. Min Act: -0.1700
Data Index: 4114800 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5284329 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3738. Min Range: -6.3738
Max Act: 5.7488. Min Act: -0.1700
Data Index: 1241713 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19