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

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

Neuron 3701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0001

Data Index: 996135 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0495. Min Act: -0.0001

Data Index: 28824 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1248603 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1278709 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1040322 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1100687 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0449. Min Act: -0.0001

Data Index: 689242 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0440. Min Act: -0.0001

Data Index: 608935 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0397. Min Act: -0.0001

Data Index: 1327442 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0454. Min Act: -0.0001

Data Index: 855760 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0419. Min Act: -0.0001

Data Index: 817748 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1072444 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1280997 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0440. Min Act: -0.0001

Data Index: 102576 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1299395 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0401. Min Act: -0.0001

Data Index: 981585 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0427. Min Act: -0.0001

Data Index: 658508 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0371. Min Act: -0.0001

Data Index: 156810 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0396. Min Act: -0.0001

Data Index: 831389 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0425. Min Act: -0.0001

Data Index: 500697 (C4 (Web Text))

Max Activating Token Index: 592