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

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

Neuron 1584 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1007756 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.3329. Min Act: -0.0000

Data Index: 369441 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.2712. Min Act: -0.0000

Data Index: 685992 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1205196 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1898. Min Act: -0.0000

Data Index: 439651 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.2374. Min Act: -0.0000

Data Index: 547595 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1884. Min Act: -0.0000

Data Index: 51016 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1870. Min Act: -0.0000

Data Index: 49340 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.2006. Min Act: -0.0000

Data Index: 766774 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1475. Min Act: -0.0000

Data Index: 250363 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1813. Min Act: -0.0000

Data Index: 1293880 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1683. Min Act: -0.0000

Data Index: 137166 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1707. Min Act: -0.0000

Data Index: 784480 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1292. Min Act: -0.0000

Data Index: 179369 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1898. Min Act: -0.0000

Data Index: 166268 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1149. Min Act: -0.0000

Data Index: 713998 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1346. Min Act: -0.0000

Data Index: 429793 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1780. Min Act: -0.0000

Data Index: 835701 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1150587 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 1.4222. Min Range: -1.4222

Max Act: 1.0482. Min Act: -0.0000

Data Index: 161284 (C4 (Web Text))

Max Activating Token Index: 724