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

Dataset: The Pile

Neuron 925 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2610. Min Act: -0.0000

Data Index: 348689 (The Pile)

Max Activating Token Index: 784

Text #1

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1250745 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1023091 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1285329 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2058. Min Act: -0.0000

Data Index: 806685 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1339664 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1892. Min Act: -0.0000

Data Index: 916380 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1649. Min Act: -0.0000

Data Index: 634829 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1849. Min Act: -0.0000

Data Index: 66138 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1819. Min Act: -0.0000

Data Index: 320505 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1399785 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1997601 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1866843 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1640. Min Act: -0.0000

Data Index: 756877 (The Pile)

Max Activating Token Index: 616

Text #14

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1627. Min Act: -0.0000

Data Index: 187232 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1423133 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1720. Min Act: -0.0000

Data Index: 482199 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1955533 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1816. Min Act: -0.0000

Data Index: 30021 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1471. Min Act: -0.0000

Data Index: 77360 (The Pile)

Max Activating Token Index: 1014