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

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

Neuron 5280 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0714. Min Act: -0.0000

Data Index: 865526 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1279553 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1336686 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0587. Min Act: -0.0000

Data Index: 727315 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0584. Min Act: -0.0000

Data Index: 80634 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0595. Min Act: -0.0000

Data Index: 886720 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0595. Min Act: -0.0000

Data Index: 485602 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0684. Min Act: -0.0000

Data Index: 499051 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0591. Min Act: -0.0000

Data Index: 409678 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0639. Min Act: -0.0000

Data Index: 986840 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0592. Min Act: -0.0000

Data Index: 428898 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0543. Min Act: -0.0000

Data Index: 283194 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0597. Min Act: -0.0000

Data Index: 453297 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1247250 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0563. Min Act: -0.0000

Data Index: 21281 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0520. Min Act: -0.0000

Data Index: 121334 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0598. Min Act: -0.0000

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0504. Min Act: -0.0000

Data Index: 16456 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0548. Min Act: -0.0000

Data Index: 771157 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0524. Min Act: -0.0000

Data Index: 553517 (C4 (Web Text))

Max Activating Token Index: 259