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

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

Neuron 1986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2497. Min Act: -0.0000

Data Index: 197495 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1130415 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2119. Min Act: -0.0000

Data Index: 516638 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2021. Min Act: -0.0000

Data Index: 746660 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1275971 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1931. Min Act: -0.0000

Data Index: 690309 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1919. Min Act: -0.0000

Data Index: 886710 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1918. Min Act: -0.0000

Data Index: 159737 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1042794 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1825. Min Act: -0.0000

Data Index: 731214 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1073875 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1821. Min Act: -0.0000

Data Index: 961050 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1776. Min Act: -0.0000

Data Index: 862428 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1711. Min Act: -0.0000

Data Index: 27046 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1068976 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1740. Min Act: -0.0000

Data Index: 923708 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1027992 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1658. Min Act: -0.0000

Data Index: 163160 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1757. Min Act: -0.0000

Data Index: 114668 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1795. Min Act: -0.0000

Data Index: 750160 (C4 (Web Text))

Max Activating Token Index: 938