Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4029 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0003

Data Index: 1174966 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0743. Min Act: -0.0003

Data Index: 447510 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0712. Min Act: -0.0002

Data Index: 730625 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1044089 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0691. Min Act: -0.0002

Data Index: 280404 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1130571 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1176553 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0675. Min Act: -0.0002

Data Index: 149850 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1227222 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0641. Min Act: -0.0003

Data Index: 961825 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1068706 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0591. Min Act: -0.0003

Data Index: 523768 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1144957 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0581. Min Act: -0.0003

Data Index: 358117 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0574. Min Act: -0.0003

Data Index: 320863 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0638. Min Act: -0.0003

Data Index: 717460 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0612. Min Act: -0.0002

Data Index: 825252 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0584. Min Act: -0.0003

Data Index: 256677 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0603. Min Act: -0.0003

Data Index: 965983 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0554. Min Act: -0.0003

Data Index: 853363 (C4 (Web Text))

Max Activating Token Index: 592