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

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

Neuron 2595 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: 0.2900. Min Range: -0.2900

Max Act: 0.2163. Min Act: -0.0001

Data Index: 32594 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0002

Data Index: 1065952 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2558. Min Act: -0.0001

Data Index: 477473 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2334. Min Act: -0.0001

Data Index: 766531 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2508. Min Act: -0.0002

Data Index: 1244766 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2777. Min Act: -0.0001

Data Index: 579050 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2465. Min Act: -0.0002

Data Index: 415694 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2415. Min Act: -0.0002

Data Index: 1102839 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2474. Min Act: -0.0002

Data Index: 23750 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2373. Min Act: -0.0001

Data Index: 202211 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1943. Min Act: -0.0002

Data Index: 491902 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2325. Min Act: -0.0001

Data Index: 113779 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1853. Min Act: -0.0001

Data Index: 677854 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1738. Min Act: -0.0001

Data Index: 125224 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2306. Min Act: -0.0002

Data Index: 449011 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2198. Min Act: -0.0001

Data Index: 485973 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2104. Min Act: -0.0002

Data Index: 399744 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2122. Min Act: -0.0001

Data Index: 182304 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2192. Min Act: -0.0001

Data Index: 66337 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1865. Min Act: -0.0002

Data Index: 1346129 (C4 (Web Text))

Max Activating Token Index: 797