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

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

Neuron 1829 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: 0.0789. Min Range: -0.0789

Max Act: 0.0789. Min Act: -0.0002

Data Index: 478141 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0731. Min Act: -0.0002

Data Index: 881424 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1455248 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0628. Min Act: -0.0002

Data Index: 840447 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0707. Min Act: -0.0002

Data Index: 31283 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1196065 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0661. Min Act: -0.0002

Data Index: 214624 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0604. Min Act: -0.0002

Data Index: 586026 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1198996 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0629. Min Act: -0.0002

Data Index: 560082 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0646. Min Act: -0.0002

Data Index: 969950 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0672. Min Act: -0.0002

Data Index: 792259 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1374912 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0642. Min Act: -0.0002

Data Index: 502608 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0631. Min Act: -0.0002

Data Index: 376345 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1108253 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1183866 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0626. Min Act: -0.0002

Data Index: 906547 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0607. Min Act: -0.0002

Data Index: 817790 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0601. Min Act: -0.0002

Data Index: 749407 (C4 (Web Text))

Max Activating Token Index: 844