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

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

Neuron 1437 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: 0.5430. Min Range: -0.5430

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1280744 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1333286 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1157027 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4586. Min Act: -0.0000

Data Index: 70767 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4643. Min Act: -0.0000

Data Index: 721383 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4455. Min Act: -0.0000

Data Index: 553108 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4220. Min Act: -0.0000

Data Index: 993809 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1068523 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4206. Min Act: -0.0000

Data Index: 786458 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3895. Min Act: -0.0000

Data Index: 12433 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1598933 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4317. Min Act: -0.0000

Data Index: 835360 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3690. Min Act: -0.0000

Data Index: 181941 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1441931 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1612737 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3738. Min Act: -0.0000

Data Index: 988524 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1601601 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1435495 (Python Code)

Max Activating Token Index: 794

Text #18

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1081391 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.3813. Min Act: -0.0000

Data Index: 894433 (C4 (Web Text))

Max Activating Token Index: 509