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

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

Neuron 784 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1122391 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0782. Min Act: -0.0001

Data Index: 429801 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0702. Min Act: -0.0001

Data Index: 424315 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0730. Min Act: -0.0001

Data Index: 598455 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0644. Min Act: -0.0001

Data Index: 642919 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1057911 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1300228 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0610. Min Act: -0.0001

Data Index: 461057 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0621. Min Act: -0.0001

Data Index: 954839 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0580. Min Act: -0.0001

Data Index: 725615 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0600. Min Act: -0.0001

Data Index: 970313 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0549. Min Act: -0.0001

Data Index: 760714 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0575. Min Act: -0.0001

Data Index: 106010 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0554. Min Act: -0.0001

Data Index: 716896 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0551. Min Act: -0.0001

Data Index: 682864 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0528. Min Act: -0.0001

Data Index: 71164 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1055449 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0495. Min Act: -0.0001

Data Index: 260602 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0548. Min Act: -0.0001

Data Index: 789013 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0462. Min Act: -0.0001

Data Index: 734271 (C4 (Web Text))

Max Activating Token Index: 792