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

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

Neuron 2830 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: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0002

Data Index: 703492 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1048440 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0768. Min Act: -0.0002

Data Index: 348046 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0740. Min Act: -0.0002

Data Index: 927991 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0754. Min Act: -0.0002

Data Index: 888067 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0799. Min Act: -0.0002

Data Index: 436876 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0762. Min Act: -0.0002

Data Index: 44210 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0742. Min Act: -0.0002

Data Index: 886234 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0734. Min Act: -0.0002

Data Index: 68783 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1209975 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0736. Min Act: -0.0002

Data Index: 873826 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0700. Min Act: -0.0002

Data Index: 137223 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0723. Min Act: -0.0002

Data Index: 549353 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0700. Min Act: -0.0002

Data Index: 580688 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0745. Min Act: -0.0002

Data Index: 723250 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1005653 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0741. Min Act: -0.0002

Data Index: 474529 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0634. Min Act: -0.0002

Data Index: 823381 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1255168 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0703. Min Act: -0.0002

Data Index: 367747 (C4 (Web Text))

Max Activating Token Index: 610