Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2255 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6477. Min Range: -10.6477
Max Act: 10.6477. Min Act: -0.1700
Data Index: 1008163 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6477. Min Range: -10.6477
Max Act: 10.2102. Min Act: -0.1700
Data Index: 7093460 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6477. Min Range: -10.6477
Max Act: 10.0852. Min Act: -0.1700
Data Index: 4831193 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6477. Min Range: -10.6477
Max Act: 10.0852. Min Act: -0.1700
Data Index: 2840898 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6477. Min Range: -10.6477
Max Act: 10.0227. Min Act: -0.1700
Data Index: 3154437 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6477. Min Range: -10.6477
Max Act: 10.0227. Min Act: -0.1700
Data Index: 6147804 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6477. Min Range: -10.6477
Max Act: 10.0227. Min Act: -0.1700
Data Index: 8197402 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.9602. Min Act: -0.1700
Data Index: 7246053 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.8977. Min Act: -0.1700
Data Index: 4492083 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.8352. Min Act: -0.1700
Data Index: 6627028 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.8352. Min Act: -0.1700
Data Index: 3429335 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7727. Min Act: -0.1700
Data Index: 7823401 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7727. Min Act: -0.1700
Data Index: 5362387 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7727. Min Act: -0.1700
Data Index: 5924697 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7727. Min Act: -0.1700
Data Index: 3772117 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7102. Min Act: -0.1700
Data Index: 1857542 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7102. Min Act: -0.1700
Data Index: 6618755 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7102. Min Act: -0.1700
Data Index: 3239436 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.6477. Min Act: -0.1700
Data Index: 7351552 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6477. Min Range: -10.6477
Max Act: 9.7102. Min Act: -0.1700
Data Index: 8569763 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19