Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 673 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0002

Data Index: 579589 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0779. Min Act: -0.0002

Data Index: 800136 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0770. Min Act: -0.0002

Data Index: 118496 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0770. Min Act: -0.0002

Data Index: 520382 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0722. Min Act: -0.0002

Data Index: 537542 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0701. Min Act: -0.0002

Data Index: 695044 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0711. Min Act: -0.0002

Data Index: 551163 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0718. Min Act: -0.0002

Data Index: 798187 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1593454 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0674. Min Act: -0.0002

Data Index: 933877 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0684. Min Act: -0.0002

Data Index: 293871 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0673. Min Act: -0.0002

Data Index: 614865 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1497466 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1408312 (Python Code)

Max Activating Token Index: 518

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0689. Min Act: -0.0002

Data Index: 797029 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0683. Min Act: -0.0002

Data Index: 969456 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0681. Min Act: -0.0002

Data Index: 196952 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0668. Min Act: -0.0002

Data Index: 699657 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1041071 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1612302 (Python Code)

Max Activating Token Index: 408