Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1293 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1678. Min Act: -0.0002

Data Index: 1217808 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1523. Min Act: -0.0002

Data Index: 628766 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1596. Min Act: -0.0002

Data Index: 1156175 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1453. Min Act: -0.0001

Data Index: 750567 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1467. Min Act: -0.0002

Data Index: 559977 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1500. Min Act: -0.0002

Data Index: 781546 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1388. Min Act: -0.0002

Data Index: 222510 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1114408 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1323. Min Act: -0.0002

Data Index: 589175 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1248. Min Act: -0.0002

Data Index: 1041463 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1234. Min Act: -0.0002

Data Index: 928359 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1277. Min Act: -0.0002

Data Index: 1250674 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1225. Min Act: -0.0002

Data Index: 402824 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1260. Min Act: -0.0001

Data Index: 3971 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1248. Min Act: -0.0002

Data Index: 123986 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1223. Min Act: -0.0002

Data Index: 450581 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1072389 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1134907 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1185. Min Act: -0.0002

Data Index: 308250 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1219. Min Act: -0.0002

Data Index: 564293 (C4 (Web Text))

Max Activating Token Index: 958