Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1232 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0001

Data Index: 295749 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1415. Min Act: -0.0001

Data Index: 102201 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1426. Min Act: -0.0001

Data Index: 208517 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1295. Min Act: 0.0000

Data Index: 738724 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1310. Min Act: -0.0001

Data Index: 722288 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1304. Min Act: -0.0001

Data Index: 33765 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1013730 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1188. Min Act: -0.0001

Data Index: 452959 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1211. Min Act: -0.0001

Data Index: 829863 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1215. Min Act: -0.0001

Data Index: 664748 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1010291 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1181. Min Act: -0.0001

Data Index: 69290 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1179. Min Act: -0.0001

Data Index: 139673 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1349115 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1179. Min Act: -0.0001

Data Index: 905258 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1174. Min Act: 0.0000

Data Index: 461538 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1091248 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1238232 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1194. Min Act: -0.0000

Data Index: 369631 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1126. Min Act: -0.0001

Data Index: 624488 (C4 (Web Text))

Max Activating Token Index: 436