Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1220 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.2553. Min Act: -0.0001

Data Index: 496344 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1027793 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.2226. Min Act: -0.0001

Data Index: 25523 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1894. Min Act: -0.0001

Data Index: 817212 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1345524 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1996. Min Act: -0.0001

Data Index: 791389 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1824. Min Act: -0.0001

Data Index: 232776 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1915. Min Act: -0.0001

Data Index: 93443 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.2029. Min Act: -0.0001

Data Index: 221602 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1888. Min Act: -0.0001

Data Index: 980804 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1288550 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1654502 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1810. Min Act: -0.0001

Data Index: 358833 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1290495 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1810. Min Act: -0.0001

Data Index: 812312 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1338783 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1707. Min Act: -0.0001

Data Index: 916712 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1836. Min Act: -0.0001

Data Index: 866679 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1344179 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.2553. Min Range: -0.2553

Max Act: 0.1799. Min Act: -0.0001

Data Index: 470416 (C4 (Web Text))

Max Activating Token Index: 1008