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

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

Neuron 638 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: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0002

Data Index: 106658 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0769. Min Act: -0.0002

Data Index: 248276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0821. Min Act: -0.0001

Data Index: 956757 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1009903 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0778. Min Act: -0.0001

Data Index: 766898 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0718. Min Act: -0.0001

Data Index: 687174 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0731. Min Act: -0.0002

Data Index: 429973 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1004008 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0709. Min Act: -0.0002

Data Index: 811073 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0709. Min Act: -0.0001

Data Index: 806549 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1275684 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0682. Min Act: -0.0002

Data Index: 711291 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1034054 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0652. Min Act: -0.0002

Data Index: 738926 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0651. Min Act: -0.0002

Data Index: 840440 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0668. Min Act: -0.0002

Data Index: 971009 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0644. Min Act: -0.0002

Data Index: 395389 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0642. Min Act: -0.0001

Data Index: 852524 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1038556 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0678. Min Act: -0.0001

Data Index: 126224 (C4 (Web Text))

Max Activating Token Index: 483