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

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

Neuron 3871 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: 0.0829. Min Range: -0.0829

Max Act: 0.0829. Min Act: -0.0002

Data Index: 978481 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1111366 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0679. Min Act: -0.0002

Data Index: 884265 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0707. Min Act: -0.0002

Data Index: 586821 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0719. Min Act: -0.0002

Data Index: 310229 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1038864 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0663. Min Act: -0.0002

Data Index: 147492 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0619. Min Act: -0.0002

Data Index: 496104 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0632. Min Act: -0.0002

Data Index: 291502 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0661. Min Act: -0.0002

Data Index: 412013 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0647. Min Act: -0.0002

Data Index: 385626 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1062734 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1246154 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1302841 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0669. Min Act: -0.0002

Data Index: 268050 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0599. Min Act: -0.0002

Data Index: 503979 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1143446 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1200445 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0687. Min Act: -0.0002

Data Index: 39728 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0636. Min Act: -0.0002

Data Index: 291219 (C4 (Web Text))

Max Activating Token Index: 319