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

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

Neuron 3124 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: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0000

Data Index: 485619 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0000

Data Index: 368476 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1267641 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1012248 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1232221 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1308. Min Act: -0.0000

Data Index: 941987 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1299. Min Act: -0.0000

Data Index: 127771 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1311. Min Act: -0.0000

Data Index: 637123 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1274. Min Act: -0.0000

Data Index: 752540 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1350705 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1197079 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1246. Min Act: -0.0000

Data Index: 51458 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1243. Min Act: -0.0000

Data Index: 369267 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1219. Min Act: -0.0001

Data Index: 365199 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1213. Min Act: -0.0000

Data Index: 58042 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1242. Min Act: -0.0000

Data Index: 729490 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1183. Min Act: -0.0000

Data Index: 579960 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1232268 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1170. Min Act: -0.0000

Data Index: 119784 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1077396 (C4 (Web Text))

Max Activating Token Index: 124