Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1704 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.1779. Min Act: -0.0001

Data Index: 363768 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.1712. Min Act: -0.0001

Data Index: 930917 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.9818. Min Act: -0.0001

Data Index: 674418 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0629. Min Act: -0.0001

Data Index: 1500774 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0524. Min Act: -0.0001

Data Index: 1652426 (Python Code)

Max Activating Token Index: 298

Text #5

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0584. Min Act: -0.0001

Data Index: 794344 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.9914. Min Act: -0.0001

Data Index: 1011789 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0133. Min Act: -0.0001

Data Index: 1576892 (Python Code)

Max Activating Token Index: 620

Text #8

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0394. Min Act: -0.0001

Data Index: 1534668 (Python Code)

Max Activating Token Index: 951

Text #9

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0532. Min Act: -0.0001

Data Index: 1513253 (Python Code)

Max Activating Token Index: 982

Text #10

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0541. Min Act: -0.0001

Data Index: 1450815 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.9596. Min Act: -0.0001

Data Index: 1505968 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 1.1779. Min Range: -1.1779

Max Act: 1.0101. Min Act: -0.0001

Data Index: 1540438 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.8696. Min Act: -0.0001

Data Index: 1540347 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.9718. Min Act: -0.0001

Data Index: 395615 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.9641. Min Act: -0.0001

Data Index: 465132 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.9106. Min Act: -0.0001

Data Index: 1255755 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.8583. Min Act: -0.0001

Data Index: 1542975 (Python Code)

Max Activating Token Index: 798

Text #18

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1650415 (Python Code)

Max Activating Token Index: 694

Text #19

Max Range: 1.1779. Min Range: -1.1779

Max Act: 0.9304. Min Act: -0.0001

Data Index: 1314190 (C4 (Web Text))

Max Activating Token Index: 62