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

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

Neuron 1079 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: 0.0837. Min Range: -0.0837

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1303327 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0818. Min Act: -0.0003

Data Index: 1014219 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0832. Min Act: -0.0003

Data Index: 688606 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1053139 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0773. Min Act: -0.0003

Data Index: 712351 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0733. Min Act: -0.0003

Data Index: 974428 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0763. Min Act: -0.0003

Data Index: 582033 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0728. Min Act: -0.0003

Data Index: 585469 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1081428 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0704. Min Act: -0.0003

Data Index: 18566 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0748. Min Act: -0.0003

Data Index: 806711 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0729. Min Act: -0.0003

Data Index: 993374 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0729. Min Act: -0.0003

Data Index: 608452 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0703. Min Act: -0.0003

Data Index: 168659 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0741. Min Act: -0.0003

Data Index: 182039 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0723. Min Act: -0.0003

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1252541 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0710. Min Act: -0.0003

Data Index: 124615 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0720. Min Act: -0.0003

Data Index: 920093 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0708. Min Act: -0.0004

Data Index: 642030 (C4 (Web Text))

Max Activating Token Index: 776