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

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

Neuron 4579 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1751. Min Act: -0.0002

Data Index: 458037 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1647. Min Act: -0.0002

Data Index: 229488 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1571. Min Act: -0.0002

Data Index: 804235 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1754. Min Act: -0.0002

Data Index: 142369 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1564. Min Act: -0.0002

Data Index: 332618 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1561. Min Act: -0.0002

Data Index: 229453 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1591. Min Act: -0.0002

Data Index: 1138877 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1492. Min Act: -0.0002

Data Index: 1136699 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1543. Min Act: -0.0002

Data Index: 28923 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1619. Min Act: -0.0002

Data Index: 219630 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1453. Min Act: -0.0002

Data Index: 1253639 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1441. Min Act: -0.0002

Data Index: 642974 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1325. Min Act: -0.0002

Data Index: 893540 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1434. Min Act: -0.0002

Data Index: 635775 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1422. Min Act: -0.0002

Data Index: 552352 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1513. Min Act: -0.0002

Data Index: 1146896 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1354. Min Act: -0.0002

Data Index: 267350 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1399. Min Act: -0.0002

Data Index: 995629 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1349. Min Act: -0.0002

Data Index: 70402 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1255. Min Act: -0.0002

Data Index: 809428 (C4 (Web Text))

Max Activating Token Index: 778