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

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

Neuron 60 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: 0.1038. Min Range: -0.1038

Max Act: 0.1022. Min Act: -0.0002

Data Index: 442542 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0002

Data Index: 211490 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1082905 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0862. Min Act: -0.0002

Data Index: 610274 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0690. Min Act: -0.0002

Data Index: 125635 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0735. Min Act: -0.0002

Data Index: 614830 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0758. Min Act: -0.0002

Data Index: 58125 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0796. Min Act: -0.0002

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0732. Min Act: -0.0002

Data Index: 662087 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0731. Min Act: -0.0002

Data Index: 576204 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0766. Min Act: -0.0002

Data Index: 79948 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1199055 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1031676 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0742. Min Act: -0.0002

Data Index: 197211 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0671. Min Act: -0.0002

Data Index: 66631 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0694. Min Act: -0.0002

Data Index: 89819 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1002593 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1123438 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1323966 (C4 (Web Text))

Max Activating Token Index: 180