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

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

Neuron 629 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.9372. Min Act: -0.0000

Data Index: 384996 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.8727. Min Act: -0.0000

Data Index: 1300631 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.6196. Min Act: -0.0000

Data Index: 1072690 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.4554. Min Act: -0.0000

Data Index: 559726 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1154404 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1299659 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.5003. Min Act: -0.0000

Data Index: 775349 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.3060. Min Act: -0.0000

Data Index: 519179 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1326824 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.5676. Min Act: -0.0000

Data Index: 1169961 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.3802. Min Act: -0.0000

Data Index: 70285 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.4187. Min Act: -0.0000

Data Index: 315458 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.3661. Min Act: -0.0000

Data Index: 1045221 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1255220 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1056917 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.2792. Min Act: -0.0000

Data Index: 721019 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.2728. Min Act: -0.0000

Data Index: 226341 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.4357. Min Act: -0.0000

Data Index: 576185 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.3521. Min Act: -0.0000

Data Index: 610868 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.9372. Min Range: -1.9372

Max Act: 1.2745. Min Act: -0.0000

Data Index: 802439 (C4 (Web Text))

Max Activating Token Index: 740