Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2979 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.8923. Min Act: -0.0000

Data Index: 1109726 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.7935. Min Act: -0.0000

Data Index: 1213542 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.5149. Min Act: -0.0000

Data Index: 1127437 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.4925. Min Act: -0.0000

Data Index: 332951 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3656. Min Act: -0.0000

Data Index: 920172 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3909. Min Act: -0.0000

Data Index: 933850 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1299893 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3458. Min Act: -0.0000

Data Index: 834169 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3096. Min Act: -0.0000

Data Index: 100591 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.3044. Min Act: -0.0000

Data Index: 961813 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2972. Min Act: -0.0000

Data Index: 414014 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1323999 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2426. Min Act: -0.0000

Data Index: 458390 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2822. Min Act: -0.0000

Data Index: 165994 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1274. Min Act: -0.0000

Data Index: 504918 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1057. Min Act: -0.0000

Data Index: 953254 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.2456. Min Act: -0.0000

Data Index: 95235 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1630. Min Act: -0.0000

Data Index: 579091 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1010972 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.8923. Min Range: -1.8923

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1008703 (C4 (Web Text))

Max Activating Token Index: 182