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

Dataset: The Pile

Neuron 1714 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: 1.4329. Min Range: -1.4329

Max Act: 1.4329. Min Act: -0.0000

Data Index: 725358 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3106. Min Act: -0.0000

Data Index: 21901 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1864089 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1882709 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1719583 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2338. Min Act: -0.0000

Data Index: 231341 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.3403. Min Act: -0.0000

Data Index: 984388 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1372164 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2239. Min Act: -0.0000

Data Index: 1784907 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1981058 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1164566 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1855. Min Act: -0.0000

Data Index: 1772388 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1186. Min Act: -0.0000

Data Index: 605137 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.0928. Min Act: -0.0000

Data Index: 21016 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2307. Min Act: -0.0000

Data Index: 92094 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1556. Min Act: -0.0000

Data Index: 2682 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.2246. Min Act: -0.0000

Data Index: 305518 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9484. Min Act: -0.0000

Data Index: 679800 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1512997 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1308. Min Act: -0.0000

Data Index: 402835 (The Pile)

Max Activating Token Index: 79