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

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

Neuron 1828 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0667. Min Act: -0.0005

Data Index: 108726 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0633. Min Act: -0.0006

Data Index: 259265 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0660. Min Act: -0.0005

Data Index: 959144 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0006

Data Index: 1225689 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0608. Min Act: -0.0006

Data Index: 1234386 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0564. Min Act: -0.0006

Data Index: 1286986 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0610. Min Act: -0.0006

Data Index: 989465 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0614. Min Act: -0.0006

Data Index: 156497 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0590. Min Act: -0.0006

Data Index: 866869 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0573. Min Act: -0.0006

Data Index: 687248 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0583. Min Act: -0.0006

Data Index: 317712 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0582. Min Act: -0.0006

Data Index: 920615 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0588. Min Act: -0.0006

Data Index: 571239 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0567. Min Act: -0.0006

Data Index: 431976 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0590. Min Act: -0.0005

Data Index: 640626 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0567. Min Act: -0.0006

Data Index: 886986 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0524. Min Act: -0.0006

Data Index: 512647 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0552. Min Act: -0.0005

Data Index: 203933 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0562. Min Act: -0.0005

Data Index: 962136 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0542. Min Act: -0.0006

Data Index: 721519 (C4 (Web Text))

Max Activating Token Index: 641