Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 476 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0002

Data Index: 153059 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0611. Min Act: -0.0002

Data Index: 570324 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0610. Min Act: -0.0002

Data Index: 100700 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1292524 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1515405 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1123692 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1127242 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0541. Min Act: -0.0002

Data Index: 903877 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1026305 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0531. Min Act: -0.0002

Data Index: 232664 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1203664 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0489. Min Act: -0.0002

Data Index: 109724 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0496. Min Act: -0.0002

Data Index: 173735 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1340615 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0495. Min Act: -0.0002

Data Index: 794504 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0477. Min Act: -0.0002

Data Index: 647054 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1117357 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1239495 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0467. Min Act: -0.0002

Data Index: 400454 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1390790 (Python Code)

Max Activating Token Index: 422