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

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

Neuron 3886 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2255. Min Act: -0.0000

Data Index: 49071 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2043. Min Act: -0.0000

Data Index: 16278 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1859. Min Act: -0.0000

Data Index: 290505 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1187474 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1656155 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1204675 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1838. Min Act: -0.0000

Data Index: 835062 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1769. Min Act: -0.0000

Data Index: 123420 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1298494 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1719. Min Act: -0.0000

Data Index: 444271 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1632976 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1520220 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1388612 (Python Code)

Max Activating Token Index: 841

Text #13

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1643. Min Act: -0.0000

Data Index: 103777 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1693. Min Act: -0.0000

Data Index: 987355 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1650. Min Act: -0.0000

Data Index: 617886 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1258867 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1499. Min Act: -0.0000

Data Index: 6727 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1251460 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1570. Min Act: -0.0000

Data Index: 382633 (C4 (Web Text))

Max Activating Token Index: 783