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

Dataset: The Pile

Neuron 3820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.9131. Min Act: -0.0000

Data Index: 66257 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1763491 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.6155. Min Act: -0.0000

Data Index: 1662195 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.5989. Min Act: -0.0000

Data Index: 10014 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.4139. Min Act: -0.0000

Data Index: 1790330 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.4782. Min Act: -0.0000

Data Index: 343406 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1995869 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.3273. Min Act: -0.0000

Data Index: 604655 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1147743 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1711385 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1893. Min Act: -0.0000

Data Index: 395947 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1453. Min Act: -0.0000

Data Index: 696674 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1020768 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1593913 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1586634 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1161. Min Act: -0.0000

Data Index: 352483 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1928. Min Act: -0.0000

Data Index: 27888 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.2563. Min Act: -0.0000

Data Index: 637893 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1690901 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.9131. Min Range: -1.9131

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1878703 (The Pile)

Max Activating Token Index: 985