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

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

Neuron 3815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1539. Min Act: -0.0000

Data Index: 390469 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1071067 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1362. Min Act: -0.0000

Data Index: 346252 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1396. Min Act: -0.0000

Data Index: 534909 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1401. Min Act: -0.0001

Data Index: 54839 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1056564 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1322995 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1278. Min Act: -0.0000

Data Index: 382681 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1292. Min Act: -0.0000

Data Index: 367 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1279. Min Act: -0.0001

Data Index: 187557 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1254. Min Act: -0.0001

Data Index: 207518 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1298. Min Act: -0.0000

Data Index: 525119 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1148848 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1245. Min Act: -0.0000

Data Index: 644169 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1206. Min Act: -0.0000

Data Index: 905254 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1001443 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1219. Min Act: -0.0000

Data Index: 898464 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1225. Min Act: -0.0000

Data Index: 242153 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1180. Min Act: -0.0000

Data Index: 703418 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.1539. Min Range: -0.1539

Max Act: 0.1217. Min Act: -0.0000

Data Index: 348812 (C4 (Web Text))

Max Activating Token Index: 126