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

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

Neuron 4649 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: 0.0707. Min Range: -0.0707

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1476889 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1080933 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1453923 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1412886 (Python Code)

Max Activating Token Index: 178

Text #4

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1465877 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0611. Min Act: -0.0002

Data Index: 692482 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1485236 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1164001 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1486296 (Python Code)

Max Activating Token Index: 899

Text #9

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1507461 (Python Code)

Max Activating Token Index: 750

Text #10

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1387779 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1530133 (Python Code)

Max Activating Token Index: 580

Text #12

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1632798 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1419691 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1625921 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1484434 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1426110 (Python Code)

Max Activating Token Index: 496

Text #17

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1624040 (Python Code)

Max Activating Token Index: 47

Text #18

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1652308 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 0.0707. Min Range: -0.0707

Max Act: 0.0557. Min Act: -0.0002

Data Index: 718575 (C4 (Web Text))

Max Activating Token Index: 946