Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1475 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0725. Min Act: -0.0001

Data Index: 412565 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0002

Data Index: 908995 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0691. Min Act: -0.0002

Data Index: 845201 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0706. Min Act: -0.0002

Data Index: 310076 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0670. Min Act: -0.0002

Data Index: 862028 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0652. Min Act: -0.0002

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0653. Min Act: -0.0002

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1243613 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0659. Min Act: -0.0002

Data Index: 374601 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0685. Min Act: -0.0002

Data Index: 516109 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0605. Min Act: -0.0002

Data Index: 430303 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0631. Min Act: -0.0002

Data Index: 577538 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0633. Min Act: -0.0002

Data Index: 328986 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0649. Min Act: -0.0002

Data Index: 771413 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0619. Min Act: -0.0002

Data Index: 12609 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0566. Min Act: -0.0002

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0606. Min Act: -0.0002

Data Index: 684209 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0638. Min Act: -0.0002

Data Index: 814050 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0635. Min Act: -0.0002

Data Index: 912964 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0599. Min Act: -0.0002

Data Index: 160745 (C4 (Web Text))

Max Activating Token Index: 1005