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

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

Neuron 1429 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: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1122782 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0875. Min Act: -0.0002

Data Index: 683097 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0880. Min Act: -0.0002

Data Index: 355674 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0864. Min Act: -0.0002

Data Index: 247060 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1277227 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1131864 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0811. Min Act: -0.0002

Data Index: 660612 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0800. Min Act: -0.0002

Data Index: 899631 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0786. Min Act: -0.0002

Data Index: 852744 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0759. Min Act: -0.0002

Data Index: 117149 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0767. Min Act: -0.0002

Data Index: 883887 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0775. Min Act: -0.0002

Data Index: 541146 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0779. Min Act: -0.0002

Data Index: 225510 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0796. Min Act: -0.0002

Data Index: 506448 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0768. Min Act: -0.0002

Data Index: 643710 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1019895 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0722. Min Act: -0.0002

Data Index: 625142 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0772. Min Act: -0.0002

Data Index: 138452 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0711. Min Act: -0.0002

Data Index: 747834 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0763. Min Act: -0.0002

Data Index: 182167 (C4 (Web Text))

Max Activating Token Index: 255