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

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

Neuron 611 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: 0.1653. Min Range: -0.1653

Max Act: 0.1653. Min Act: -0.0000

Data Index: 130390 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1073126 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1507. Min Act: -0.0000

Data Index: 690353 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1085851 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1456. Min Act: 0.0000

Data Index: 1168353 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1355. Min Act: -0.0000

Data Index: 175270 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1441. Min Act: -0.0000

Data Index: 847261 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1308. Min Act: 0.0000

Data Index: 307418 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1386. Min Act: -0.0000

Data Index: 982094 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1274. Min Act: -0.0000

Data Index: 621393 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1313. Min Act: -0.0000

Data Index: 521324 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1301. Min Act: 0.0000

Data Index: 1113705 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1295. Min Act: 0.0000

Data Index: 1101423 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1220. Min Act: -0.0000

Data Index: 588483 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1211. Min Act: 0.0000

Data Index: 901564 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1302. Min Act: -0.0000

Data Index: 633885 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1035089 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1208. Min Act: 0.0000

Data Index: 611520 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1158. Min Act: 0.0000

Data Index: 570196 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.1653. Min Range: -0.1653

Max Act: 0.1253. Min Act: -0.0000

Data Index: 74193 (C4 (Web Text))

Max Activating Token Index: 150