Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 674 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2370. Min Act: -0.0003

Data Index: 874188 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1899. Min Act: -0.0003

Data Index: 469470 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1754. Min Act: -0.0003

Data Index: 465409 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2021. Min Act: -0.0003

Data Index: 1298267 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2165. Min Act: -0.0003

Data Index: 1207330 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1941. Min Act: -0.0003

Data Index: 1262951 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2028. Min Act: -0.0003

Data Index: 1257482 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1937. Min Act: -0.0003

Data Index: 1156543 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1943. Min Act: -0.0003

Data Index: 502594 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1876. Min Act: -0.0003

Data Index: 754545 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1871. Min Act: -0.0003

Data Index: 102432 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1740. Min Act: -0.0003

Data Index: 289855 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1858. Min Act: -0.0003

Data Index: 92036 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1895. Min Act: -0.0003

Data Index: 1055794 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1821. Min Act: -0.0003

Data Index: 350012 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1714. Min Act: -0.0003

Data Index: 671565 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1817. Min Act: -0.0003

Data Index: 527473 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1909. Min Act: -0.0003

Data Index: 1179533 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1933. Min Act: -0.0003

Data Index: 56124 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1855. Min Act: -0.0003

Data Index: 106022 (C4 (Web Text))

Max Activating Token Index: 962