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

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

Neuron 695 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: 0.0820. Min Range: -0.0820

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0796. Min Act: -0.0003

Data Index: 82278 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1091088 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0771. Min Act: -0.0003

Data Index: 878003 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0763. Min Act: -0.0003

Data Index: 486731 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0765. Min Act: -0.0003

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0739. Min Act: -0.0003

Data Index: 814857 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0750. Min Act: -0.0002

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0735. Min Act: -0.0003

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0720. Min Act: -0.0003

Data Index: 127355 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0714. Min Act: -0.0003

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0709. Min Act: -0.0003

Data Index: 716055 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0657. Min Act: -0.0003

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0697. Min Act: -0.0003

Data Index: 502125 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0702. Min Act: -0.0003

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0711. Min Act: -0.0002

Data Index: 267534 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0694. Min Act: -0.0003

Data Index: 606738 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0671. Min Act: -0.0002

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0682. Min Act: -0.0003

Data Index: 577346 (C4 (Web Text))

Max Activating Token Index: 958