Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 10 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0897. Min Act: -0.0000

Data Index: 470224 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0856. Min Act: -0.0000

Data Index: 485288 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0852. Min Act: -0.0000

Data Index: 108570 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0789. Min Act: 0.0000

Data Index: 348518 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0825. Min Act: -0.0000

Data Index: 79920 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0731. Min Act: -0.0000

Data Index: 608868 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0704. Min Act: 0.0000

Data Index: 581591 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0704. Min Act: -0.0000

Data Index: 844726 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0668. Min Act: -0.0000

Data Index: 940741 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0639. Min Act: -0.0000

Data Index: 593651 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0602. Min Act: -0.0000

Data Index: 921274 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0619. Min Act: 0.0000

Data Index: 371323 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0640. Min Act: -0.0000

Data Index: 484534 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1032079 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0637. Min Act: -0.0000

Data Index: 547458 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0610. Min Act: -0.0000

Data Index: 795338 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0609. Min Act: -0.0000

Data Index: 428591 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0614. Min Act: -0.0000

Data Index: 470013 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0573. Min Act: -0.0000

Data Index: 752911 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1077890 (C4 (Web Text))

Max Activating Token Index: 81