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

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

Neuron 3108 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0002

Data Index: 79363 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0721. Min Act: -0.0002

Data Index: 272474 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1039254 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0709. Min Act: -0.0002

Data Index: 367162 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1028362 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0688. Min Act: -0.0002

Data Index: 536066 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0683. Min Act: -0.0002

Data Index: 421908 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0743. Min Act: -0.0002

Data Index: 135941 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0756. Min Act: -0.0002

Data Index: 384950 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0750. Min Act: -0.0002

Data Index: 417527 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1087787 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1346961 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0715. Min Act: -0.0002

Data Index: 257359 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0661. Min Act: -0.0002

Data Index: 967136 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1137495 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1131294 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0608. Min Act: -0.0002

Data Index: 590527 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0706. Min Act: -0.0002

Data Index: 968680 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1098463 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0650. Min Act: -0.0002

Data Index: 3576 (C4 (Web Text))

Max Activating Token Index: 892