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

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

Neuron 1442 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1416443 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1645587 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1471545 (Python Code)

Max Activating Token Index: 653

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1519678 (Python Code)

Max Activating Token Index: 264

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1470813 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1626131 (Python Code)

Max Activating Token Index: 328

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1468022 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1418221 (Python Code)

Max Activating Token Index: 974

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1515594 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1561349 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1446945 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1656397 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1393498 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1445698 (Python Code)

Max Activating Token Index: 564

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1428333 (Python Code)

Max Activating Token Index: 234

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1467405 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1501056 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1533728 (Python Code)

Max Activating Token Index: 286

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1476765 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1600547 (Python Code)

Max Activating Token Index: 328