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

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

Neuron 3749 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1276614 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1270636 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1480. Min Act: -0.0000

Data Index: 80200 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1538. Min Act: -0.0000

Data Index: 940335 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1129468 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1393. Min Act: -0.0000

Data Index: 665725 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1295. Min Act: -0.0000

Data Index: 368050 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1038969 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1205. Min Act: -0.0000

Data Index: 813605 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1259521 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1031525 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1081. Min Act: -0.0001

Data Index: 834444 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1166. Min Act: -0.0000

Data Index: 830207 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1216. Min Act: -0.0000

Data Index: 409377 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1226. Min Act: -0.0000

Data Index: 276818 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1148. Min Act: -0.0000

Data Index: 309576 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1227064 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1169. Min Act: -0.0000

Data Index: 721715 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1240. Min Act: -0.0000

Data Index: 537005 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.1568. Min Range: -0.1568

Max Act: 0.1103. Min Act: -0.0000

Data Index: 915258 (C4 (Web Text))

Max Activating Token Index: 900