Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2199 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.9017. Min Act: -0.1700
Data Index: 1055566 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.8705. Min Act: -0.1700
Data Index: 3409884 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.8705. Min Act: -0.1700
Data Index: 397392 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.8080. Min Act: -0.1700
Data Index: 8466620 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.7455. Min Act: -0.1700
Data Index: 1537980 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.7142. Min Act: -0.1700
Data Index: 2162295 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.7142. Min Act: -0.1700
Data Index: 935818 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.6517. Min Act: -0.1700
Data Index: 555807 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.6517. Min Act: -0.1700
Data Index: 4605762 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.6830. Min Act: -0.1700
Data Index: 6932298 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.6205. Min Act: -0.1700
Data Index: 6728937 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.6205. Min Act: -0.1700
Data Index: 6913025 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.5892. Min Act: -0.1700
Data Index: 8346102 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.6205. Min Act: -0.1700
Data Index: 1916063 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.5580. Min Act: -0.1700
Data Index: 6021655 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.6205. Min Act: -0.1700
Data Index: 3414547 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.5892. Min Act: -0.1700
Data Index: 5455269 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.5580. Min Act: -0.1700
Data Index: 2910975 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.5580. Min Act: -0.1700
Data Index: 274117 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9017. Min Range: -5.9017
Max Act: 5.5580. Min Act: -0.1700
Data Index: 5006984 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19