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

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

Neuron 758 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: 0.0869. Min Range: -0.0869

Max Act: 0.0826. Min Act: -0.0002

Data Index: 471567 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0002

Data Index: 422588 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0790. Min Act: -0.0002

Data Index: 941184 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1407001 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0856. Min Act: -0.0002

Data Index: 216461 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1135342 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0732. Min Act: -0.0002

Data Index: 630022 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0786. Min Act: -0.0002

Data Index: 194696 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0750. Min Act: -0.0002

Data Index: 655168 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0732. Min Act: -0.0002

Data Index: 544858 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0804. Min Act: -0.0002

Data Index: 366121 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1328120 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1120725 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0703. Min Act: -0.0002

Data Index: 271739 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0720. Min Act: -0.0002

Data Index: 502278 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0724. Min Act: -0.0002

Data Index: 806281 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0698. Min Act: -0.0002

Data Index: 913274 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0756. Min Act: -0.0002

Data Index: 15243 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0721. Min Act: -0.0002

Data Index: 565730 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0695. Min Act: -0.0002

Data Index: 387910 (C4 (Web Text))

Max Activating Token Index: 671