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

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

Neuron 1192 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: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0001

Data Index: 310346 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0801. Min Act: -0.0002

Data Index: 316034 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1312167 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1178063 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0782. Min Act: -0.0002

Data Index: 530261 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0765. Min Act: -0.0001

Data Index: 370330 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0755. Min Act: -0.0002

Data Index: 194789 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1219179 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0759. Min Act: -0.0001

Data Index: 473640 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0736. Min Act: -0.0002

Data Index: 16365 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0766. Min Act: -0.0001

Data Index: 579274 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0741. Min Act: -0.0001

Data Index: 663538 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0742. Min Act: -0.0002

Data Index: 543505 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0726. Min Act: -0.0000

Data Index: 843858 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1169809 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1047420 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0720. Min Act: -0.0002

Data Index: 744260 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0723. Min Act: -0.0001

Data Index: 402243 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0711. Min Act: -0.0001

Data Index: 782080 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0704. Min Act: -0.0001

Data Index: 940771 (C4 (Web Text))

Max Activating Token Index: 463