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

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

Neuron 729 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: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0002

Data Index: 779223 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0814. Min Act: -0.0002

Data Index: 668670 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0750. Min Act: -0.0002

Data Index: 442259 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1053244 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0685. Min Act: -0.0001

Data Index: 699739 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0665. Min Act: -0.0002

Data Index: 842381 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0677. Min Act: -0.0002

Data Index: 137511 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0723. Min Act: -0.0002

Data Index: 189076 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0708. Min Act: -0.0002

Data Index: 461425 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0684. Min Act: -0.0002

Data Index: 899530 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0659. Min Act: -0.0002

Data Index: 144204 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0650. Min Act: -0.0002

Data Index: 223661 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1161691 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0636. Min Act: -0.0002

Data Index: 384116 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1357628 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1207299 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0676. Min Act: -0.0002

Data Index: 359721 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0655. Min Act: -0.0002

Data Index: 343876 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1163018 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1272636 (C4 (Web Text))

Max Activating Token Index: 628