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

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

Neuron 543 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: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0005

Data Index: 1256883 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0753. Min Act: -0.0005

Data Index: 103731 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0766. Min Act: -0.0005

Data Index: 751590 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0764. Min Act: -0.0005

Data Index: 1098469 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0758. Min Act: -0.0005

Data Index: 270426 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0689. Min Act: -0.0005

Data Index: 1242547 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0728. Min Act: -0.0004

Data Index: 700208 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0734. Min Act: -0.0005

Data Index: 1320106 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0710. Min Act: -0.0005

Data Index: 29612 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0687. Min Act: -0.0005

Data Index: 606745 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0710. Min Act: -0.0005

Data Index: 206107 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0693. Min Act: -0.0005

Data Index: 1117402 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0707. Min Act: -0.0005

Data Index: 562107 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0674. Min Act: -0.0005

Data Index: 399958 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0688. Min Act: -0.0005

Data Index: 914889 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0666. Min Act: -0.0005

Data Index: 878682 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0657. Min Act: -0.0005

Data Index: 153847 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0625. Min Act: -0.0005

Data Index: 714734 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0652. Min Act: -0.0005

Data Index: 459860 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0637. Min Act: -0.0005

Data Index: 96120 (C4 (Web Text))

Max Activating Token Index: 308