Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2657 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1724. Min Act: -0.0001

Data Index: 513003 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1494. Min Act: -0.0001

Data Index: 541858 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1560. Min Act: -0.0001

Data Index: 975966 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1551. Min Act: -0.0001

Data Index: 687407 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1391. Min Act: -0.0001

Data Index: 558718 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1497596 (Python Code)

Max Activating Token Index: 753

Text #6

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1426494 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1646623 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1526. Min Act: -0.0001

Data Index: 644637 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1204253 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1211. Min Act: -0.0001

Data Index: 387621 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1325393 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1398. Min Act: -0.0001

Data Index: 944623 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1369643 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1225. Min Act: -0.0001

Data Index: 451285 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1340. Min Act: -0.0000

Data Index: 715189 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1604596 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1229137 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1158. Min Act: -0.0001

Data Index: 176103 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1235155 (C4 (Web Text))

Max Activating Token Index: 91