Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2022 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0000

Data Index: 404195 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1465. Min Act: -0.0000

Data Index: 121841 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1392. Min Act: -0.0000

Data Index: 376199 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1257. Min Act: -0.0000

Data Index: 421820 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1382. Min Act: -0.0000

Data Index: 21216 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1343. Min Act: -0.0000

Data Index: 551173 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1273. Min Act: -0.0000

Data Index: 559662 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1259. Min Act: -0.0000

Data Index: 310994 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1336. Min Act: -0.0000

Data Index: 198402 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1224. Min Act: -0.0000

Data Index: 424307 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1297. Min Act: -0.0000

Data Index: 977203 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1250. Min Act: -0.0000

Data Index: 757899 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1205. Min Act: -0.0000

Data Index: 248054 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1246. Min Act: -0.0000

Data Index: 412107 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1201. Min Act: -0.0000

Data Index: 390464 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1278. Min Act: -0.0000

Data Index: 722768 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1275. Min Act: -0.0000

Data Index: 726687 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1327. Min Act: -0.0000

Data Index: 125918 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1254774 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1231575 (C4 (Web Text))

Max Activating Token Index: 252