Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1382 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1536. Min Act: -0.0000

Data Index: 559422 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1541. Min Act: -0.0001

Data Index: 406353 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1402. Min Act: -0.0001

Data Index: 718444 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1129527 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1217. Min Act: -0.0001

Data Index: 404929 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1341. Min Act: -0.0001

Data Index: 625496 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1300. Min Act: -0.0001

Data Index: 211835 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1005838 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1197. Min Act: -0.0001

Data Index: 450469 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1234. Min Act: -0.0001

Data Index: 594987 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1264. Min Act: -0.0000

Data Index: 399400 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1033463 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1220. Min Act: -0.0001

Data Index: 563184 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1223464 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1198221 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1170. Min Act: -0.0001

Data Index: 312212 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1127. Min Act: -0.0000

Data Index: 861748 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1124. Min Act: -0.0001

Data Index: 324374 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1210. Min Act: -0.0001

Data Index: 723397 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1021386 (C4 (Web Text))

Max Activating Token Index: 580