Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 407 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0002

Data Index: 658125 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1129. Min Act: -0.0002

Data Index: 494226 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1015. Min Act: -0.0001

Data Index: 372715 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0987. Min Act: -0.0002

Data Index: 357481 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0922. Min Act: -0.0001

Data Index: 929560 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0904. Min Act: -0.0001

Data Index: 677595 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1039723 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1075585 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0822. Min Act: -0.0001

Data Index: 798708 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1003371 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0801. Min Act: -0.0002

Data Index: 463274 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0815. Min Act: -0.0001

Data Index: 510050 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1352417 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0767. Min Act: -0.0001

Data Index: 396969 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1241659 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0779. Min Act: -0.0002

Data Index: 446592 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1186040 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0743. Min Act: -0.0001

Data Index: 444825 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1226691 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0713. Min Act: -0.0001

Data Index: 185432 (C4 (Web Text))

Max Activating Token Index: 764