Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2026 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0769. Min Act: -0.0003

Data Index: 396146 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0729. Min Act: -0.0003

Data Index: 572529 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0705. Min Act: -0.0004

Data Index: 786251 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0686. Min Act: -0.0004

Data Index: 282247 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0654. Min Act: -0.0003

Data Index: 794041 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0661. Min Act: -0.0003

Data Index: 565519 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0666. Min Act: -0.0003

Data Index: 399530 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0661. Min Act: -0.0003

Data Index: 306548 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0639. Min Act: -0.0004

Data Index: 37115 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0637. Min Act: -0.0003

Data Index: 991913 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0643. Min Act: -0.0003

Data Index: 471101 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0613. Min Act: -0.0004

Data Index: 647451 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0622. Min Act: -0.0003

Data Index: 263306 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0619. Min Act: -0.0003

Data Index: 84347 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1288810 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0637. Min Act: -0.0003

Data Index: 668428 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0642. Min Act: -0.0003

Data Index: 920106 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0623. Min Act: -0.0003

Data Index: 197740 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0630. Min Act: -0.0004

Data Index: 740971 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.0769. Min Range: -0.0769

Max Act: 0.0611. Min Act: -0.0004

Data Index: 197583 (C4 (Web Text))

Max Activating Token Index: 729