Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1407. Min Act: -0.0000

Data Index: 119716 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1350. Min Act: -0.0000

Data Index: 385072 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1381. Min Act: -0.0000

Data Index: 337592 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1244578 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1295780 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1307. Min Act: -0.0000

Data Index: 501689 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1302. Min Act: -0.0000

Data Index: 102064 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1246. Min Act: -0.0000

Data Index: 759889 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1303. Min Act: -0.0000

Data Index: 843929 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1082872 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1266. Min Act: -0.0000

Data Index: 360115 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1131198 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1331480 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1236. Min Act: -0.0000

Data Index: 929271 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1226. Min Act: -0.0001

Data Index: 344776 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1358076 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1198. Min Act: -0.0001

Data Index: 632269 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1180. Min Act: -0.0000

Data Index: 729807 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1103. Min Act: -0.0000

Data Index: 10718 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1173. Min Act: -0.0000

Data Index: 447510 (C4 (Web Text))

Max Activating Token Index: 968