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

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

Neuron 1999 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: 0.1416. Min Range: -0.1416

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1127069 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1409. Min Act: -0.0002

Data Index: 184830 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: -0.0002

Data Index: 1163829 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1308. Min Act: -0.0002

Data Index: 203519 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1242. Min Act: -0.0002

Data Index: 587899 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1377. Min Act: -0.0002

Data Index: 778087 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1313. Min Act: -0.0002

Data Index: 828622 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1245. Min Act: -0.0002

Data Index: 798870 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1282. Min Act: -0.0002

Data Index: 294308 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1384. Min Act: -0.0002

Data Index: 1064552 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1365. Min Act: -0.0002

Data Index: 594631 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1391. Min Act: -0.0002

Data Index: 760982 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1332874 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1187008 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1231. Min Act: -0.0002

Data Index: 596329 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1219. Min Act: -0.0002

Data Index: 954514 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1351368 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1227. Min Act: -0.0002

Data Index: 460780 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1153824 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1185. Min Act: -0.0002

Data Index: 745233 (C4 (Web Text))

Max Activating Token Index: 17