Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 168 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0588. Min Act: -0.0003

Data Index: 732309 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0573. Min Act: -0.0003

Data Index: 871989 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0555. Min Act: -0.0003

Data Index: 391623 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0515. Min Act: -0.0004

Data Index: 1197254 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0487. Min Act: -0.0004

Data Index: 1207553 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0481. Min Act: -0.0003

Data Index: 937798 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1200928 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0506. Min Act: -0.0003

Data Index: 77477 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0467. Min Act: -0.0003

Data Index: 491220 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0474. Min Act: -0.0003

Data Index: 886051 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0492. Min Act: -0.0003

Data Index: 489512 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0003

Data Index: 101726 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0003

Data Index: 458646 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0463. Min Act: -0.0004

Data Index: 402143 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0427. Min Act: -0.0003

Data Index: 300421 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0438. Min Act: -0.0003

Data Index: 483400 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0449. Min Act: -0.0003

Data Index: 656397 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1134610 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0441. Min Act: -0.0003

Data Index: 459534 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0588. Min Range: -0.0588

Max Act: 0.0490. Min Act: -0.0003

Data Index: 353227 (C4 (Web Text))

Max Activating Token Index: 198