Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 566 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0744. Min Act: -0.0003

Data Index: 25004 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0785. Min Act: -0.0003

Data Index: 63635 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1430143 (Python Code)

Max Activating Token Index: 824

Text #3

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1173222 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0780. Min Act: -0.0003

Data Index: 766003 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0768. Min Act: -0.0003

Data Index: 297051 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0765. Min Act: -0.0003

Data Index: 973600 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1612039 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1645751 (Python Code)

Max Activating Token Index: 638

Text #9

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0758. Min Act: -0.0003

Data Index: 183663 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1432657 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0771. Min Act: -0.0003

Data Index: 753322 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0746. Min Act: -0.0003

Data Index: 577955 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1374396 (Python Code)

Max Activating Token Index: 793

Text #14

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0759. Min Act: -0.0003

Data Index: 2007 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0756. Min Act: -0.0003

Data Index: 355723 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0745. Min Act: -0.0002

Data Index: 436041 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1408031 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0740. Min Act: -0.0003

Data Index: 1327979 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0736. Min Act: -0.0003

Data Index: 967060 (C4 (Web Text))

Max Activating Token Index: 856