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

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

Neuron 2701 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0688. Min Act: -0.0002

Data Index: 312976 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0707. Min Act: -0.0002

Data Index: 638457 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1437456 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0672. Min Act: -0.0002

Data Index: 418496 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1260796 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0656. Min Act: -0.0002

Data Index: 167880 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0625. Min Act: -0.0002

Data Index: 50577 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0625. Min Act: -0.0002

Data Index: 386883 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1533990 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0646. Min Act: -0.0002

Data Index: 659717 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0639. Min Act: -0.0002

Data Index: 74047 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1080664 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1375322 (Python Code)

Max Activating Token Index: 750

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0630. Min Act: -0.0002

Data Index: 254878 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1418712 (Python Code)

Max Activating Token Index: 581

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0627. Min Act: -0.0002

Data Index: 44920 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0626. Min Act: -0.0002

Data Index: 843514 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0627. Min Act: -0.0002

Data Index: 210857 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1180589 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0619. Min Act: -0.0002

Data Index: 739104 (C4 (Web Text))

Max Activating Token Index: 764