Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3724 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.2121. Min Act: -0.0002

Data Index: 208342 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1810. Min Act: -0.0002

Data Index: 750579 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1615. Min Act: -0.0002

Data Index: 1187485 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1342868 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1726. Min Act: -0.0002

Data Index: 725480 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1303053 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1690. Min Act: -0.0002

Data Index: 177924 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1251461 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1654. Min Act: -0.0001

Data Index: 316044 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1055811 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1549. Min Act: -0.0002

Data Index: 487535 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1539. Min Act: -0.0002

Data Index: 582204 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1527. Min Act: -0.0002

Data Index: 948636 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1635. Min Act: -0.0002

Data Index: 297226 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1019891 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1603. Min Act: -0.0002

Data Index: 683066 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1286. Min Act: -0.0001

Data Index: 605797 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1548. Min Act: -0.0001

Data Index: 279282 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1590. Min Act: -0.0002

Data Index: 581792 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.2121. Min Range: -0.2121

Max Act: 0.1474. Min Act: -0.0002

Data Index: 9645 (C4 (Web Text))

Max Activating Token Index: 957