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

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

Neuron 5069 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0779. Min Act: -0.0002

Data Index: 349381 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0811. Min Act: -0.0002

Data Index: 938411 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1089331 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0721. Min Act: -0.0002

Data Index: 939470 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0706. Min Act: -0.0003

Data Index: 975218 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0683. Min Act: -0.0003

Data Index: 156713 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0700. Min Act: -0.0003

Data Index: 126885 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0638. Min Act: -0.0002

Data Index: 856076 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0684. Min Act: -0.0003

Data Index: 283745 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0674. Min Act: -0.0002

Data Index: 163005 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0694. Min Act: -0.0003

Data Index: 37845 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0620. Min Act: -0.0003

Data Index: 159900 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0656. Min Act: -0.0002

Data Index: 753323 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0652. Min Act: -0.0003

Data Index: 766197 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0645. Min Act: -0.0003

Data Index: 171083 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0653. Min Act: -0.0003

Data Index: 884619 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0652. Min Act: -0.0003

Data Index: 936619 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1203714 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1211125 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0640. Min Act: -0.0003

Data Index: 44170 (C4 (Web Text))

Max Activating Token Index: 895