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

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

Neuron 2028 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: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0003

Data Index: 420568 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0855. Min Act: -0.0003

Data Index: 305525 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0831. Min Act: -0.0004

Data Index: 1308760 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0812. Min Act: -0.0003

Data Index: 221004 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0809. Min Act: -0.0003

Data Index: 340018 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0833. Min Act: -0.0003

Data Index: 942123 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0796. Min Act: -0.0003

Data Index: 824552 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0826. Min Act: -0.0003

Data Index: 1341855 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1149846 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0801. Min Act: -0.0003

Data Index: 912477 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0790. Min Act: -0.0004

Data Index: 249854 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1345368 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1213692 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0803. Min Act: -0.0003

Data Index: 713164 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0733. Min Act: -0.0004

Data Index: 277573 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0784. Min Act: -0.0003

Data Index: 717945 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0752. Min Act: -0.0004

Data Index: 1206596 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0745. Min Act: -0.0003

Data Index: 265459 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0764. Min Act: -0.0003

Data Index: 252016 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0767. Min Act: -0.0003

Data Index: 389932 (C4 (Web Text))

Max Activating Token Index: 674