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

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

Neuron 1654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1399. Min Act: -0.0003

Data Index: 484469 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1394. Min Act: -0.0003

Data Index: 190170 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1332. Min Act: -0.0003

Data Index: 347384 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1274. Min Act: -0.0003

Data Index: 1068865 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1362. Min Act: -0.0003

Data Index: 109192 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1301. Min Act: -0.0003

Data Index: 593304 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1239. Min Act: -0.0003

Data Index: 690411 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1247. Min Act: -0.0003

Data Index: 589780 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1240. Min Act: -0.0002

Data Index: 460584 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1266. Min Act: -0.0003

Data Index: 1077010 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1140329 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1216. Min Act: -0.0002

Data Index: 207106 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1288701 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1189. Min Act: -0.0003

Data Index: 753384 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1230. Min Act: -0.0003

Data Index: 209108 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1206. Min Act: -0.0002

Data Index: 768995 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1245. Min Act: -0.0003

Data Index: 490006 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1205. Min Act: -0.0003

Data Index: 316373 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1198. Min Act: -0.0003

Data Index: 348786 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.1399. Min Range: -0.1399

Max Act: 0.1206. Min Act: -0.0003

Data Index: 178915 (C4 (Web Text))

Max Activating Token Index: 280