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

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

Neuron 4620 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1614. Min Act: -0.0003

Data Index: 826449 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1665. Min Act: -0.0003

Data Index: 555466 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1523. Min Act: -0.0003

Data Index: 363644 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1454. Min Act: -0.0003

Data Index: 962367 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1452. Min Act: -0.0003

Data Index: 876342 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1403. Min Act: -0.0003

Data Index: 816079 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1344. Min Act: -0.0003

Data Index: 854303 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1375. Min Act: -0.0003

Data Index: 249468 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1181976 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1323. Min Act: -0.0002

Data Index: 572997 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1314. Min Act: -0.0003

Data Index: 626495 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1220. Min Act: -0.0003

Data Index: 833596 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1164. Min Act: -0.0003

Data Index: 323721 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1341. Min Act: -0.0003

Data Index: 519015 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1241. Min Act: -0.0003

Data Index: 612249 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1275. Min Act: -0.0003

Data Index: 922196 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1197. Min Act: -0.0003

Data Index: 466096 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1231. Min Act: -0.0003

Data Index: 430463 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1143. Min Act: -0.0003

Data Index: 581310 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1217. Min Act: -0.0003

Data Index: 77413 (C4 (Web Text))

Max Activating Token Index: 743