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

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

Neuron 3430 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1431003 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1402729 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1437512 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1634106 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1506849 (Python Code)

Max Activating Token Index: 1022

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1625167 (Python Code)

Max Activating Token Index: 324

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1619779 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1493515 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0723. Min Act: -0.0002

Data Index: 791339 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0663. Min Act: -0.0002

Data Index: 148122 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1632243 (Python Code)

Max Activating Token Index: 694

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1647846 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1500210 (Python Code)

Max Activating Token Index: 447

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0513. Min Act: -0.0002

Data Index: 217591 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0637. Min Act: -0.0002

Data Index: 681228 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1607847 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1464310 (Python Code)

Max Activating Token Index: 909

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1448274 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0586. Min Act: -0.0002

Data Index: 981760 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0632. Min Act: -0.0002

Data Index: 988258 (C4 (Web Text))

Max Activating Token Index: 898