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

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

Neuron 963 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0817. Min Act: -0.0005

Data Index: 1249933 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0005

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0821. Min Act: -0.0005

Data Index: 436535 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0806. Min Act: -0.0005

Data Index: 1350458 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0770. Min Act: -0.0005

Data Index: 272141 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0772. Min Act: -0.0005

Data Index: 75896 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0824. Min Act: -0.0005

Data Index: 1046637 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0788. Min Act: -0.0005

Data Index: 1101470 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0785. Min Act: -0.0005

Data Index: 1102342 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0798. Min Act: -0.0005

Data Index: 889746 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0757. Min Act: -0.0005

Data Index: 857890 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0750. Min Act: -0.0005

Data Index: 662039 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0803. Min Act: -0.0005

Data Index: 559232 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0716. Min Act: -0.0005

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0761. Min Act: -0.0005

Data Index: 886227 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0770. Min Act: -0.0005

Data Index: 904491 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0824. Min Act: -0.0005

Data Index: 1199961 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0810. Min Act: -0.0005

Data Index: 480033 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0809. Min Act: -0.0005

Data Index: 325488 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0714. Min Act: -0.0005

Data Index: 179188 (C4 (Web Text))

Max Activating Token Index: 125