Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4363 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1120837 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0732. Min Act: -0.0002

Data Index: 541923 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0596. Min Act: -0.0002

Data Index: 431842 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0653. Min Act: -0.0002

Data Index: 961682 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0650. Min Act: -0.0002

Data Index: 291510 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1197444 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0596. Min Act: -0.0002

Data Index: 198210 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0002

Data Index: 297797 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0734. Min Act: -0.0002

Data Index: 89220 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1094913 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0730. Min Act: -0.0002

Data Index: 77791 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0763. Min Act: -0.0002

Data Index: 505179 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1033339 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0647. Min Act: -0.0002

Data Index: 44393 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0568. Min Act: -0.0002

Data Index: 316816 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0574. Min Act: -0.0002

Data Index: 405506 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0537. Min Act: -0.0002

Data Index: 614930 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0531. Min Act: -0.0002

Data Index: 298903 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1315989 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0484. Min Act: -0.0002

Data Index: 130346 (C4 (Web Text))

Max Activating Token Index: 836