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

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

Neuron 1707 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1193545 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0788. Min Act: -0.0002

Data Index: 878061 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1187162 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0793. Min Act: -0.0002

Data Index: 799042 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0782. Min Act: -0.0002

Data Index: 238978 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0686. Min Act: -0.0002

Data Index: 994639 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0743. Min Act: -0.0002

Data Index: 390644 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0791. Min Act: -0.0002

Data Index: 799623 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0754. Min Act: -0.0002

Data Index: 753556 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0743. Min Act: -0.0002

Data Index: 307175 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0707. Min Act: -0.0002

Data Index: 42775 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0687. Min Act: -0.0002

Data Index: 333928 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0715. Min Act: -0.0002

Data Index: 460889 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0714. Min Act: -0.0002

Data Index: 423203 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0763. Min Act: -0.0002

Data Index: 686098 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0717. Min Act: -0.0002

Data Index: 774406 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0755. Min Act: -0.0002

Data Index: 504431 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0726. Min Act: -0.0002

Data Index: 529839 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0680. Min Act: -0.0002

Data Index: 762241 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1123506 (C4 (Web Text))

Max Activating Token Index: 638