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

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

Neuron 3663 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0001

Data Index: 369820 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1416. Min Act: -0.0002

Data Index: 17952 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1338. Min Act: -0.0002

Data Index: 776978 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1015491 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1237894 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1313. Min Act: -0.0002

Data Index: 1308981 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1298. Min Act: -0.0002

Data Index: 905510 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1264. Min Act: -0.0002

Data Index: 11807 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1190374 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1253. Min Act: -0.0002

Data Index: 555145 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1252. Min Act: -0.0002

Data Index: 803992 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1243. Min Act: -0.0001

Data Index: 528147 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1223. Min Act: -0.0002

Data Index: 984411 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1210161 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1188. Min Act: -0.0002

Data Index: 336330 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1184. Min Act: -0.0002

Data Index: 1199525 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1022664 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1021927 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1277527 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1111684 (C4 (Web Text))

Max Activating Token Index: 425