Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0002

Data Index: 19082 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1686. Min Act: -0.0002

Data Index: 562337 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1810. Min Act: -0.0002

Data Index: 544789 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1786. Min Act: -0.0002

Data Index: 826825 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1773. Min Act: -0.0002

Data Index: 353569 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1747. Min Act: -0.0002

Data Index: 236178 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1758. Min Act: -0.0002

Data Index: 818608 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1655. Min Act: -0.0002

Data Index: 621045 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1644. Min Act: -0.0002

Data Index: 262187 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1652. Min Act: -0.0002

Data Index: 133853 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1508. Min Act: -0.0002

Data Index: 1093762 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1604. Min Act: -0.0002

Data Index: 963150 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1595. Min Act: -0.0002

Data Index: 1357831 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1578. Min Act: -0.0002

Data Index: 613267 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1502. Min Act: -0.0002

Data Index: 456468 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1602. Min Act: -0.0002

Data Index: 896536 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1551. Min Act: -0.0002

Data Index: 484065 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1559. Min Act: -0.0002

Data Index: 861164 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1626. Min Act: -0.0002

Data Index: 569787 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1609. Min Act: -0.0002

Data Index: 279709 (C4 (Web Text))

Max Activating Token Index: 1007