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

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

Neuron 3152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1364832 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1654988 (Python Code)

Max Activating Token Index: 750

Text #2

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1577290 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1242. Min Act: -0.0000

Data Index: 428169 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1594360 (Python Code)

Max Activating Token Index: 808

Text #5

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1597680 (Python Code)

Max Activating Token Index: 569

Text #6

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1517556 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1297. Min Act: -0.0000

Data Index: 400256 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1373889 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1237. Min Act: -0.0000

Data Index: 259859 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1071378 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1172011 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1211. Min Act: -0.0000

Data Index: 568845 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1504599 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1451987 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1384388 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1238. Min Act: -0.0000

Data Index: 115312 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1455068 (Python Code)

Max Activating Token Index: 112

Text #18

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1411737 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1393209 (Python Code)

Max Activating Token Index: 765