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

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

Neuron 3112 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0623. Min Range: -2.0623

Max Act: 2.0623. Min Act: -0.0000

Data Index: 1242236 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.9364. Min Act: -0.0000

Data Index: 960280 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.8334. Min Act: -0.0000

Data Index: 251236 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.7546. Min Act: -0.0000

Data Index: 660733 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.6741. Min Act: -0.0000

Data Index: 16211 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.7807. Min Act: -0.0000

Data Index: 1024586 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.7790. Min Act: -0.0000

Data Index: 467187 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.4347. Min Act: -0.0000

Data Index: 204050 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1140242 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.5446. Min Act: -0.0000

Data Index: 669066 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.5423. Min Act: -0.0000

Data Index: 867974 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1049823 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.5662. Min Act: -0.0000

Data Index: 680263 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.4746. Min Act: -0.0000

Data Index: 1045478 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.4678. Min Act: -0.0000

Data Index: 442965 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.4787. Min Act: -0.0000

Data Index: 326528 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1287548 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1097129 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.5080. Min Act: -0.0000

Data Index: 823153 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 2.0623. Min Range: -2.0623

Max Act: 1.4986. Min Act: -0.0000

Data Index: 852806 (C4 (Web Text))

Max Activating Token Index: 774