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

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

Neuron 3462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1181932 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1321. Min Act: -0.0000

Data Index: 244946 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1355. Min Act: 0.0000

Data Index: 109070 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1028101 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1253. Min Act: -0.0000

Data Index: 889333 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1000027 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1325697 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1241. Min Act: -0.0000

Data Index: 925982 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1326. Min Act: -0.0000

Data Index: 266251 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1263. Min Act: -0.0000

Data Index: 325695 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1091343 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1075325 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1223. Min Act: -0.0000

Data Index: 246386 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1228. Min Act: -0.0000

Data Index: 384199 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1199. Min Act: -0.0000

Data Index: 817554 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1296868 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1155. Min Act: -0.0000

Data Index: 98974 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1193. Min Act: -0.0000

Data Index: 596996 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1194. Min Act: -0.0000

Data Index: 512250 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1612. Min Range: -0.1612

Max Act: 0.1143. Min Act: -0.0000

Data Index: 899292 (C4 (Web Text))

Max Activating Token Index: 684