Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1327438 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1177142 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0323. Min Act: -0.0002

Data Index: 533892 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0309. Min Act: -0.0003

Data Index: 592715 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1244226 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0318. Min Act: -0.0002

Data Index: 978776 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0310. Min Act: -0.0002

Data Index: 796224 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0310. Min Act: -0.0003

Data Index: 436576 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0298. Min Act: -0.0004

Data Index: 628337 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1613571 (Python Code)

Max Activating Token Index: 658

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1183611 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0301. Min Act: -0.0002

Data Index: 700126 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1040547 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0304. Min Act: -0.0000

Data Index: 586395 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1176536 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1302297 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0292. Min Act: -0.0003

Data Index: 656548 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1245633 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0282. Min Act: -0.0003

Data Index: 643284 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0281. Min Act: -0.0002

Data Index: 602215 (C4 (Web Text))

Max Activating Token Index: 738