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

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

Neuron 1928 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1224267 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7210. Min Act: -0.0000

Data Index: 514894 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5947. Min Act: -0.0000

Data Index: 487365 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.8770. Min Act: -0.0000

Data Index: 334925 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1024588 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7248. Min Act: -0.0000

Data Index: 342419 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6055. Min Act: -0.0000

Data Index: 891153 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6920. Min Act: -0.0000

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6954. Min Act: -0.0000

Data Index: 446895 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6493. Min Act: -0.0000

Data Index: 118505 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6247. Min Act: -0.0000

Data Index: 932743 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1103519 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6189. Min Act: -0.0000

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.6476. Min Act: -0.0000

Data Index: 987842 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5954. Min Act: -0.0000

Data Index: 265580 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5958. Min Act: -0.0000

Data Index: 242169 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1137355 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5649. Min Act: -0.0000

Data Index: 49179 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5926. Min Act: -0.0000

Data Index: 610671 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.5751. Min Act: -0.0000

Data Index: 720297 (C4 (Web Text))

Max Activating Token Index: 467