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

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

Neuron 1045 in Layer 2

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: 0.0978. Min Act: -0.0002

Data Index: 1209 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0920. Min Act: -0.0002

Data Index: 609039 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0902. Min Act: -0.0002

Data Index: 932359 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0921. Min Act: -0.0002

Data Index: 387272 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0874. Min Act: -0.0002

Data Index: 786596 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0917. Min Act: -0.0002

Data Index: 272085 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0874. Min Act: -0.0002

Data Index: 657547 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1205210 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0765. Min Act: -0.0002

Data Index: 362017 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1061325 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0737. Min Act: -0.0002

Data Index: 914353 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0732. Min Act: -0.0002

Data Index: 912992 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1250530 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0746. Min Act: -0.0002

Data Index: 482031 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0725. Min Act: -0.0002

Data Index: 68830 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0755. Min Act: -0.0002

Data Index: 724802 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0727. Min Act: -0.0002

Data Index: 239191 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0767. Min Act: -0.0002

Data Index: 549956 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0719. Min Act: -0.0002

Data Index: 889874 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1177457 (C4 (Web Text))

Max Activating Token Index: 803