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

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

Neuron 45 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.9421. Min Act: -0.0001

Data Index: 1268844 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.7486. Min Act: -0.0000

Data Index: 957833 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6670. Min Act: -0.0000

Data Index: 644465 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6553. Min Act: -0.0000

Data Index: 211417 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1273522 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6258. Min Act: -0.0000

Data Index: 729645 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6606. Min Act: -0.0000

Data Index: 856793 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6216. Min Act: -0.0000

Data Index: 15867 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5693. Min Act: -0.0000

Data Index: 693701 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5589. Min Act: -0.0000

Data Index: 291253 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5941. Min Act: -0.0000

Data Index: 573495 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1231733 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5679. Min Act: -0.0000

Data Index: 833669 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5466. Min Act: -0.0000

Data Index: 680395 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6005. Min Act: -0.0000

Data Index: 667245 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5402. Min Act: -0.0000

Data Index: 118896 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.6104. Min Act: -0.0001

Data Index: 1161095 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5833. Min Act: -0.0000

Data Index: 519125 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5660. Min Act: 0.0000

Data Index: 200758 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.9421. Min Range: -0.9421

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1207629 (C4 (Web Text))

Max Activating Token Index: 9