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

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

Neuron 4320 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1779. Min Act: -0.0002

Data Index: 525442 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1622. Min Act: -0.0002

Data Index: 956373 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1592. Min Act: -0.0002

Data Index: 969699 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1535. Min Act: -0.0002

Data Index: 1039466 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1490. Min Act: -0.0002

Data Index: 1291834 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1495. Min Act: -0.0002

Data Index: 227174 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1393. Min Act: -0.0002

Data Index: 47483 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1371. Min Act: -0.0002

Data Index: 3626 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1287. Min Act: -0.0002

Data Index: 19313 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1282. Min Act: -0.0002

Data Index: 64050 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1255. Min Act: -0.0002

Data Index: 121837 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1235. Min Act: -0.0002

Data Index: 925336 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1182. Min Act: -0.0002

Data Index: 372822 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1296140 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1239. Min Act: -0.0002

Data Index: 660780 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1193. Min Act: -0.0002

Data Index: 409839 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1178. Min Act: -0.0002

Data Index: 286463 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1180. Min Act: -0.0002

Data Index: 629608 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1153. Min Act: -0.0002

Data Index: 786611 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1156. Min Act: -0.0002

Data Index: 237262 (C4 (Web Text))

Max Activating Token Index: 807