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

Dataset: The Pile

Neuron 622 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: 3.8720. Min Range: -3.8720

Max Act: 3.8720. Min Act: -0.0000

Data Index: 1039019 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.2763. Min Act: -0.0000

Data Index: 430040 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.2430. Min Act: -0.0000

Data Index: 1271261 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.3132. Min Act: -0.0000

Data Index: 1145135 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.2904. Min Act: -0.0000

Data Index: 1619775 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9789. Min Act: -0.0000

Data Index: 1403830 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.1242. Min Act: -0.0000

Data Index: 1530721 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.5676. Min Act: -0.0000

Data Index: 1044368 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9188. Min Act: -0.0000

Data Index: 54103 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.5276. Min Act: -0.0000

Data Index: 1181752 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.0440. Min Act: -0.0000

Data Index: 1894922 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.1769. Min Act: -0.0000

Data Index: 541163 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.0339. Min Act: -0.0000

Data Index: 568682 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.3098. Min Act: -0.0000

Data Index: 253971 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9542. Min Act: -0.0000

Data Index: 1428427 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9049. Min Act: -0.0000

Data Index: 543201 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 3.8720. Min Range: -3.8720

Max Act: 3.1632. Min Act: -0.0000

Data Index: 1434453 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9798. Min Act: -0.0000

Data Index: 43182 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.8358. Min Act: -0.0000

Data Index: 1631400 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 3.8720. Min Range: -3.8720

Max Act: 2.9662. Min Act: -0.0000

Data Index: 1652464 (The Pile)

Max Activating Token Index: 925