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

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

Neuron 4037 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1460. Min Act: -0.0002

Data Index: 1083593 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1517. Min Act: -0.0002

Data Index: 1085275 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1437. Min Act: -0.0002

Data Index: 52854 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1429. Min Act: -0.0002

Data Index: 600117 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1283. Min Act: -0.0002

Data Index: 711478 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1324. Min Act: -0.0002

Data Index: 202544 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1129. Min Act: -0.0002

Data Index: 3672 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1050019 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1254. Min Act: -0.0002

Data Index: 26114 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1284128 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1258. Min Act: -0.0002

Data Index: 520875 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1212. Min Act: -0.0002

Data Index: 400226 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1235447 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1255. Min Act: -0.0002

Data Index: 627645 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1111. Min Act: -0.0002

Data Index: 66591 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1131035 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1242. Min Act: -0.0002

Data Index: 371334 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1156. Min Act: -0.0002

Data Index: 818138 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1124001 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1155. Min Act: -0.0002

Data Index: 214850 (C4 (Web Text))

Max Activating Token Index: 926