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

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

Neuron 3936 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1020919 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.2126. Min Act: -0.0000

Data Index: 429661 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1182948 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1863. Min Act: -0.0001

Data Index: 980449 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1867. Min Act: -0.0000

Data Index: 445598 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1778. Min Act: -0.0000

Data Index: 573830 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1750. Min Act: -0.0000

Data Index: 957838 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1048311 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1044531 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1142926 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1608. Min Act: -0.0000

Data Index: 201625 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1667. Min Act: -0.0001

Data Index: 208999 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1241877 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1660. Min Act: -0.0000

Data Index: 25302 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1548. Min Act: -0.0000

Data Index: 712179 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1270698 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1143928 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1580. Min Act: -0.0000

Data Index: 537976 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1578. Min Act: -0.0000

Data Index: 287307 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.2340. Min Range: -0.2340

Max Act: 0.1576. Min Act: -0.0000

Data Index: 778948 (C4 (Web Text))

Max Activating Token Index: 86