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

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

Neuron 2133 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: 0.2202. Min Range: -0.2202

Max Act: 0.2202. Min Act: -0.0001

Data Index: 577798 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1621. Min Act: -0.0000

Data Index: 328780 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1492010 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1618947 (Python Code)

Max Activating Token Index: 729

Text #4

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1473439 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1568121 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1463418 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1428. Min Act: -0.0000

Data Index: 582328 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1232543 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1034880 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1302322 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1181. Min Act: -0.0000

Data Index: 254573 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1264. Min Act: -0.0001

Data Index: 755550 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1635370 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1057327 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1172. Min Act: -0.0001

Data Index: 436209 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1046. Min Act: -0.0000

Data Index: 957827 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1196648 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1125. Min Act: -0.0000

Data Index: 224561 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.2202. Min Range: -0.2202

Max Act: 0.1177. Min Act: -0.0000

Data Index: 973115 (C4 (Web Text))

Max Activating Token Index: 74