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

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

Neuron 211 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: 0.0862. Min Range: -0.0862

Max Act: 0.0856. Min Act: -0.0003

Data Index: 627192 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0003

Data Index: 54343 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1123106 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0807. Min Act: -0.0003

Data Index: 846526 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0772. Min Act: -0.0003

Data Index: 1339523 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1195004 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0746. Min Act: -0.0003

Data Index: 154131 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1310736 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0717. Min Act: -0.0003

Data Index: 734550 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0702. Min Act: -0.0002

Data Index: 476009 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0713. Min Act: -0.0003

Data Index: 579585 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0660. Min Act: -0.0002

Data Index: 430958 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0667. Min Act: -0.0002

Data Index: 874547 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0678. Min Act: -0.0002

Data Index: 367023 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0685. Min Act: -0.0003

Data Index: 55986 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1270509 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1057021 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1095039 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0645. Min Act: -0.0003

Data Index: 145842 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1287505 (C4 (Web Text))

Max Activating Token Index: 617