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

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

Neuron 4588 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: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1171816 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1440. Min Act: -0.0000

Data Index: 760424 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1397. Min Act: -0.0000

Data Index: 837544 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1267880 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1340. Min Act: -0.0000

Data Index: 625076 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1337. Min Act: -0.0000

Data Index: 222207 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1354. Min Act: -0.0000

Data Index: 201788 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1317. Min Act: -0.0000

Data Index: 495287 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1326. Min Act: -0.0000

Data Index: 69832 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1293. Min Act: -0.0000

Data Index: 703854 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1234. Min Act: -0.0000

Data Index: 151865 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1193460 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1036157 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1256. Min Act: -0.0000

Data Index: 109815 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1179813 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1224. Min Act: -0.0000

Data Index: 636064 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1228. Min Act: -0.0000

Data Index: 607326 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1210. Min Act: -0.0000

Data Index: 998580 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1214. Min Act: -0.0000

Data Index: 795875 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1149. Min Act: -0.0000

Data Index: 641522 (C4 (Web Text))

Max Activating Token Index: 662