Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2352 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.8479. Min Act: -0.1700
Data Index: 8158365 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7204. Min Act: -0.1700
Data Index: 3362507 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7524. Min Act: -0.1700
Data Index: 56602 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7204. Min Act: -0.1700
Data Index: 6195860 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.7044. Min Act: -0.1700
Data Index: 208210 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6884. Min Act: -0.1700
Data Index: 2507592 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6724. Min Act: -0.1700
Data Index: 4036605 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6724. Min Act: -0.1700
Data Index: 6233366 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6564. Min Act: -0.1700
Data Index: 6683087 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6724. Min Act: -0.1700
Data Index: 7662788 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6564. Min Act: -0.1700
Data Index: 6812721 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6242. Min Act: -0.1700
Data Index: 1481013 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6564. Min Act: -0.1700
Data Index: 1223750 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6564. Min Act: -0.1700
Data Index: 5017912 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6242. Min Act: -0.1700
Data Index: 5948318 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6724. Min Act: -0.1700
Data Index: 993479 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6564. Min Act: -0.1700
Data Index: 2782985 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6242. Min Act: -0.1700
Data Index: 7553228 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6082. Min Act: -0.1700
Data Index: 4623985 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8479. Min Range: -2.8479
Max Act: 2.6242. Min Act: -0.1700
Data Index: 3181643 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19