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

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

Neuron 2350 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1618. Min Range: -2.1618

Max Act: 2.1618. Min Act: -0.0001

Data Index: 250155 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 2.1618. Min Range: -2.1618

Max Act: 2.0855. Min Act: -0.0001

Data Index: 285957 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 2.1618. Min Range: -2.1618

Max Act: 2.0029. Min Act: -0.0001

Data Index: 1078000 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7803. Min Act: -0.0000

Data Index: 780486 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.8877. Min Act: -0.0001

Data Index: 393649 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.8854. Min Act: -0.0001

Data Index: 96637 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.8190. Min Act: -0.0000

Data Index: 1435372 (Python Code)

Max Activating Token Index: 260

Text #7

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.9178. Min Act: -0.0000

Data Index: 1264550 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.8742. Min Act: -0.0000

Data Index: 1210612 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.6962. Min Act: -0.0000

Data Index: 203612 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7949. Min Act: -0.0000

Data Index: 906996 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7283. Min Act: -0.0001

Data Index: 110446 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7733. Min Act: -0.0000

Data Index: 1322664 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.8069. Min Act: -0.0001

Data Index: 568093 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.6178. Min Act: -0.0000

Data Index: 257587 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7622. Min Act: -0.0001

Data Index: 92933 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7218. Min Act: -0.0001

Data Index: 202543 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7515. Min Act: -0.0001

Data Index: 790432 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.6809. Min Act: -0.0001

Data Index: 161440 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 2.1618. Min Range: -2.1618

Max Act: 1.7237. Min Act: -0.0001

Data Index: 520395 (C4 (Web Text))

Max Activating Token Index: 795