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

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

Neuron 764 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: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1099901 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0778. Min Act: -0.0003

Data Index: 43451 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0744. Min Act: -0.0002

Data Index: 911228 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0743. Min Act: -0.0003

Data Index: 329062 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0733. Min Act: -0.0002

Data Index: 679360 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1255333 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0729. Min Act: -0.0004

Data Index: 344473 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0735. Min Act: -0.0002

Data Index: 157301 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0697. Min Act: -0.0003

Data Index: 687497 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0686. Min Act: -0.0001

Data Index: 469738 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0694. Min Act: -0.0004

Data Index: 351632 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1232685 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0686. Min Act: -0.0002

Data Index: 395628 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1316133 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0648. Min Act: -0.0003

Data Index: 17113 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0620. Min Act: -0.0002

Data Index: 324409 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0619. Min Act: -0.0003

Data Index: 322613 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1276162 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0623. Min Act: -0.0003

Data Index: 433211 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0633. Min Act: -0.0002

Data Index: 509575 (C4 (Web Text))

Max Activating Token Index: 430