Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.6481. Min Act: -0.1700
Data Index: 3330870 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.5544. Min Act: -0.1700
Data Index: 6955181 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.3356. Min Act: -0.1700
Data Index: 7975994 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.3044. Min Act: -0.1700
Data Index: 1195466 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.2731. Min Act: -0.1700
Data Index: 269338 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.2419. Min Act: -0.1700
Data Index: 5237188 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.2419. Min Act: -0.1700
Data Index: 7957000 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.2106. Min Act: -0.1700
Data Index: 625802 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.1169. Min Act: -0.1700
Data Index: 4692678 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.1481. Min Act: -0.1700
Data Index: 4584484 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.1794. Min Act: -0.1700
Data Index: 4539863 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.0856. Min Act: -0.1700
Data Index: 2742446 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.0856. Min Act: -0.1700
Data Index: 3662906 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.0856. Min Act: -0.1700
Data Index: 7756469 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.0231. Min Act: -0.1700
Data Index: 6885597 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6481. Min Range: -5.6481
Max Act: 4.9919. Min Act: -0.1700
Data Index: 1919933 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.0231. Min Act: -0.1700
Data Index: 1627779 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6481. Min Range: -5.6481
Max Act: 4.9919. Min Act: -0.1700
Data Index: 2439867 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6481. Min Range: -5.6481
Max Act: 5.0231. Min Act: -0.1700
Data Index: 6411069 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6481. Min Range: -5.6481
Max Act: 4.9919. Min Act: -0.1700
Data Index: 310372 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19