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

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

Neuron 449 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: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0004

Data Index: 945814 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0865. Min Act: -0.0003

Data Index: 80646 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0831. Min Act: -0.0003

Data Index: 988450 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0794. Min Act: -0.0004

Data Index: 44597 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0796. Min Act: -0.0003

Data Index: 496922 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0798. Min Act: -0.0003

Data Index: 693797 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0800. Min Act: -0.0003

Data Index: 685639 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1071216 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0783. Min Act: -0.0004

Data Index: 1306822 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1543303 (Python Code)

Max Activating Token Index: 793

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0773. Min Act: -0.0003

Data Index: 939159 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0753. Min Act: -0.0003

Data Index: 245714 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1032371 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0732. Min Act: -0.0003

Data Index: 713690 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1049725 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1270993 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1031798 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0710. Min Act: -0.0003

Data Index: 950821 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0671. Min Act: -0.0004

Data Index: 580687 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0692. Min Act: -0.0003

Data Index: 872012 (C4 (Web Text))

Max Activating Token Index: 915