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

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

Neuron 1766 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0712. Min Act: -0.0001

Data Index: 844069 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0713. Min Act: -0.0001

Data Index: 983449 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0001

Data Index: 335330 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0694. Min Act: -0.0001

Data Index: 662710 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1244661 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0674. Min Act: -0.0001

Data Index: 724498 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0617. Min Act: -0.0001

Data Index: 56944 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1357199 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1254898 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0624. Min Act: -0.0001

Data Index: 785781 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1275191 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0623. Min Act: -0.0001

Data Index: 824349 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1127170 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1338604 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0637. Min Act: -0.0001

Data Index: 830580 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0594. Min Act: -0.0001

Data Index: 943380 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0611. Min Act: -0.0001

Data Index: 256163 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0589. Min Act: -0.0001

Data Index: 170562 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0607. Min Act: -0.0001

Data Index: 998879 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0601. Min Act: -0.0001

Data Index: 772924 (C4 (Web Text))

Max Activating Token Index: 577