Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1085 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0001

Data Index: 586536 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0623. Min Act: -0.0001

Data Index: 803496 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1149320 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0547. Min Act: -0.0001

Data Index: 2433 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0592. Min Act: -0.0001

Data Index: 868979 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1401835 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0561. Min Act: -0.0001

Data Index: 591554 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0560. Min Act: -0.0001

Data Index: 55904 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0591. Min Act: -0.0001

Data Index: 774621 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0573. Min Act: -0.0001

Data Index: 738527 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1426235 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0456. Min Act: -0.0001

Data Index: 220931 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0525. Min Act: -0.0001

Data Index: 120534 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0519. Min Act: -0.0001

Data Index: 463209 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1163790 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0515. Min Act: -0.0001

Data Index: 952977 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0446. Min Act: -0.0001

Data Index: 1398533 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1497841 (Python Code)

Max Activating Token Index: 655

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0447. Min Act: -0.0001

Data Index: 965048 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0523. Min Act: -0.0001

Data Index: 47203 (C4 (Web Text))

Max Activating Token Index: 550