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

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

Neuron 2922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2323. Min Act: -0.0000

Data Index: 844288 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1437522 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1608487 (Python Code)

Max Activating Token Index: 440

Text #3

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2101. Min Act: -0.0000

Data Index: 471207 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1866. Min Act: -0.0000

Data Index: 384209 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1589473 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1634. Min Act: -0.0000

Data Index: 264006 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1751. Min Act: -0.0000

Data Index: 378346 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1429196 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1707. Min Act: -0.0000

Data Index: 312082 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1342139 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1738. Min Act: -0.0000

Data Index: 816054 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1566635 (Python Code)

Max Activating Token Index: 677

Text #13

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1541197 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1577. Min Act: -0.0000

Data Index: 896140 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1070027 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1556. Min Act: -0.0000

Data Index: 596889 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1105432 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1569. Min Act: -0.0000

Data Index: 71911 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1594. Min Act: -0.0000

Data Index: 10928 (C4 (Web Text))

Max Activating Token Index: 511