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

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

Neuron 327 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0002

Data Index: 527138 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0689. Min Act: -0.0002

Data Index: 741822 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1138396 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0666. Min Act: -0.0002

Data Index: 273578 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0666. Min Act: -0.0002

Data Index: 934810 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1005473 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1131375 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0615. Min Act: -0.0002

Data Index: 444127 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0609. Min Act: -0.0001

Data Index: 631965 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0622. Min Act: -0.0002

Data Index: 565905 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0626. Min Act: -0.0002

Data Index: 854710 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0590. Min Act: -0.0002

Data Index: 37814 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0603. Min Act: -0.0002

Data Index: 250235 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0591. Min Act: -0.0002

Data Index: 795690 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0585. Min Act: -0.0002

Data Index: 115192 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1126020 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0585. Min Act: -0.0002

Data Index: 434910 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0611. Min Act: -0.0002

Data Index: 569100 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1026787 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1187214 (C4 (Web Text))

Max Activating Token Index: 447