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

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

Neuron 2875 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: 0.0785. Min Range: -0.0785

Max Act: 0.0758. Min Act: -0.0002

Data Index: 544514 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0744. Min Act: -0.0002

Data Index: 332445 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0730. Min Act: -0.0002

Data Index: 180802 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1495918 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1147709 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1065079 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0729. Min Act: -0.0002

Data Index: 512690 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0661. Min Act: -0.0002

Data Index: 981387 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1224497 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0703. Min Act: -0.0002

Data Index: 790647 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0623. Min Act: -0.0002

Data Index: 795553 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1092836 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0716. Min Act: -0.0002

Data Index: 941521 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1206934 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0646. Min Act: -0.0002

Data Index: 66269 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0654. Min Act: -0.0002

Data Index: 815568 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0731. Min Act: -0.0002

Data Index: 548593 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0674. Min Act: -0.0002

Data Index: 478830 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0678. Min Act: -0.0002

Data Index: 409580 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1403062 (Python Code)

Max Activating Token Index: 289