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

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

Neuron 2126 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0643. Min Act: -0.0000

Data Index: 1067381 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1769. Min Act: -0.0000

Data Index: 1092528 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0453. Min Act: -0.0000

Data Index: 709194 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0735. Min Act: -0.0000

Data Index: 880713 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1543. Min Act: -0.0000

Data Index: 829624 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1541. Min Act: -0.0000

Data Index: 879072 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0443. Min Act: -0.0000

Data Index: 57046 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.0491. Min Act: -0.0000

Data Index: 783764 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1225. Min Act: -0.0000

Data Index: 513884 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9806. Min Act: -0.0001

Data Index: 47569 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9649. Min Act: -0.0000

Data Index: 16596 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1261878 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9487. Min Act: -0.0000

Data Index: 813174 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1424873 (Python Code)

Max Activating Token Index: 446

Text #14

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9014. Min Act: -0.0000

Data Index: 264707 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9252. Min Act: -0.0000

Data Index: 432487 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1275824 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8862. Min Act: -0.0000

Data Index: 973213 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8914. Min Act: -0.0000

Data Index: 446758 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8948. Min Act: -0.0000

Data Index: 326879 (C4 (Web Text))

Max Activating Token Index: 714