Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5740 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1154547 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0986. Min Act: -0.0002

Data Index: 487621 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1240933 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0864. Min Act: -0.0002

Data Index: 930057 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1581117 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1197585 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0856. Min Act: -0.0002

Data Index: 630389 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0836. Min Act: -0.0002

Data Index: 389797 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0796. Min Act: -0.0002

Data Index: 7207 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0824. Min Act: -0.0002

Data Index: 49182 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1262480 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0762. Min Act: -0.0002

Data Index: 583020 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0788. Min Act: -0.0002

Data Index: 507843 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1139110 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0803. Min Act: -0.0002

Data Index: 376594 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0801. Min Act: -0.0002

Data Index: 988710 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1174915 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0738. Min Act: -0.0002

Data Index: 753406 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0759. Min Act: -0.0002

Data Index: 577594 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0756. Min Act: -0.0002

Data Index: 472191 (C4 (Web Text))

Max Activating Token Index: 592