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

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

Neuron 1805 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0005

Data Index: 548694 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0606. Min Act: -0.0005

Data Index: 1253008 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0640. Min Act: -0.0005

Data Index: 576113 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0591. Min Act: -0.0005

Data Index: 89152 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0599. Min Act: -0.0005

Data Index: 788145 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0623. Min Act: -0.0005

Data Index: 932306 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0638. Min Act: -0.0005

Data Index: 354337 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0582. Min Act: -0.0005

Data Index: 164582 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0573. Min Act: -0.0005

Data Index: 440205 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0609. Min Act: -0.0005

Data Index: 399289 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0600. Min Act: -0.0005

Data Index: 378667 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0602. Min Act: -0.0005

Data Index: 101894 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0585. Min Act: -0.0005

Data Index: 344267 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0575. Min Act: -0.0005

Data Index: 614767 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0528. Min Act: -0.0005

Data Index: 56494 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0574. Min Act: -0.0005

Data Index: 835443 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0587. Min Act: -0.0005

Data Index: 342925 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0513. Min Act: -0.0005

Data Index: 787211 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0573. Min Act: -0.0005

Data Index: 930199 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0585. Min Act: -0.0005

Data Index: 532926 (C4 (Web Text))

Max Activating Token Index: 418