Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2323 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1471. Min Act: -0.0001

Data Index: 350320 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1511. Min Act: -0.0001

Data Index: 522883 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1036642 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1241067 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1164406 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1282. Min Act: -0.0001

Data Index: 653703 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1401. Min Act: -0.0001

Data Index: 462211 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1296. Min Act: -0.0001

Data Index: 426517 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1334759 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1372. Min Act: -0.0001

Data Index: 139909 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1363. Min Act: -0.0001

Data Index: 287400 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1100977 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1289. Min Act: -0.0001

Data Index: 487522 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1285. Min Act: -0.0001

Data Index: 198705 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1065755 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1221. Min Act: -0.0000

Data Index: 736712 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1221. Min Act: -0.0001

Data Index: 357985 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1221. Min Act: -0.0001

Data Index: 897843 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1339751 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1252. Min Act: -0.0001

Data Index: 668196 (C4 (Web Text))

Max Activating Token Index: 113