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

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

Neuron 2610 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2386. Min Act: -0.0001

Data Index: 675006 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2179. Min Act: -0.0001

Data Index: 708085 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2118. Min Act: -0.0001

Data Index: 864894 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1977. Min Act: -0.0001

Data Index: 261922 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2018. Min Act: -0.0001

Data Index: 354486 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.2063. Min Act: -0.0001

Data Index: 51714 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1762. Min Act: -0.0000

Data Index: 403940 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1860. Min Act: -0.0001

Data Index: 72079 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1696. Min Act: -0.0001

Data Index: 348734 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1751. Min Act: -0.0000

Data Index: 764051 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1738. Min Act: -0.0000

Data Index: 460073 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1732. Min Act: -0.0000

Data Index: 634297 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1193445 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1654. Min Act: -0.0000

Data Index: 26543 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1656. Min Act: -0.0000

Data Index: 322354 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1684. Min Act: -0.0000

Data Index: 791535 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1023173 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1683. Min Act: -0.0000

Data Index: 818862 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1675. Min Act: -0.0000

Data Index: 279012 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.2386. Min Range: -0.2386

Max Act: 0.1618. Min Act: -0.0000

Data Index: 317188 (C4 (Web Text))

Max Activating Token Index: 722