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

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

Neuron 3788 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: 0.0816. Min Range: -0.0816

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1019051 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0747. Min Act: -0.0002

Data Index: 634153 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1093312 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0772. Min Act: -0.0002

Data Index: 156166 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0002

Data Index: 935532 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0698. Min Act: -0.0002

Data Index: 884172 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1240470 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0663. Min Act: -0.0002

Data Index: 717397 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0646. Min Act: -0.0002

Data Index: 896709 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0752. Min Act: -0.0002

Data Index: 43287 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0544. Min Act: -0.0002

Data Index: 114806 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0631. Min Act: -0.0002

Data Index: 319195 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0709. Min Act: -0.0002

Data Index: 704 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0719. Min Act: -0.0002

Data Index: 848431 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1070326 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1358862 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1245909 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1019733 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1248262 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0649. Min Act: -0.0002

Data Index: 914628 (C4 (Web Text))

Max Activating Token Index: 117