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

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

Neuron 169 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: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0002

Data Index: 995319 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0671. Min Act: -0.0002

Data Index: 949230 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1333421 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0669. Min Act: -0.0002

Data Index: 110959 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0631. Min Act: -0.0002

Data Index: 764463 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0623. Min Act: -0.0002

Data Index: 616541 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0674. Min Act: -0.0002

Data Index: 982511 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0663. Min Act: -0.0002

Data Index: 551658 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1056078 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0653. Min Act: -0.0002

Data Index: 614111 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0623. Min Act: -0.0002

Data Index: 158841 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0617. Min Act: -0.0002

Data Index: 731892 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0604. Min Act: -0.0002

Data Index: 586968 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1441823 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1181434 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1555717 (Python Code)

Max Activating Token Index: 927

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0573. Min Act: -0.0002

Data Index: 880377 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0553. Min Act: -0.0002

Data Index: 843798 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1362871 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0538. Min Act: -0.0002

Data Index: 721043 (C4 (Web Text))

Max Activating Token Index: 815