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

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

Neuron 609 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: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0002

Data Index: 418235 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0888. Min Act: -0.0002

Data Index: 796758 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1338242 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0838. Min Act: -0.0002

Data Index: 798235 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1000912 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0806. Min Act: -0.0002

Data Index: 258316 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0703. Min Act: -0.0002

Data Index: 439414 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1017763 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0745. Min Act: -0.0002

Data Index: 35549 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1220102 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0732. Min Act: -0.0002

Data Index: 469475 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0728. Min Act: -0.0002

Data Index: 150111 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1142697 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0722. Min Act: -0.0002

Data Index: 473019 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0610. Min Act: -0.0002

Data Index: 559862 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0647. Min Act: -0.0002

Data Index: 521463 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0646. Min Act: -0.0002

Data Index: 981319 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0638. Min Act: -0.0002

Data Index: 41369 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1231400 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0685. Min Act: -0.0002

Data Index: 262203 (C4 (Web Text))

Max Activating Token Index: 545