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

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

Neuron 2218 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0969. Min Act: -0.0000

Data Index: 504382 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0000

Data Index: 372187 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1002608 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0964. Min Act: -0.0000

Data Index: 93465 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0967. Min Act: -0.0000

Data Index: 494496 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0875. Min Act: -0.0000

Data Index: 53129 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0872. Min Act: -0.0000

Data Index: 978766 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0847. Min Act: -0.0000

Data Index: 579027 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0798. Min Act: -0.0000

Data Index: 918795 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1217098 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0785. Min Act: -0.0000

Data Index: 659502 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0751. Min Act: -0.0000

Data Index: 778626 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1247898 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0797. Min Act: -0.0000

Data Index: 282934 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1073657 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1354958 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0759. Min Act: -0.0000

Data Index: 493568 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1094941 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0702. Min Act: -0.0000

Data Index: 589872 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0752. Min Act: -0.0000

Data Index: 413032 (C4 (Web Text))

Max Activating Token Index: 701