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

Dataset: The Pile

Neuron 3423 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.3061. Min Act: -0.0000

Data Index: 50320 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2168. Min Act: -0.0000

Data Index: 1391376 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1716. Min Act: -0.0000

Data Index: 1682686 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1534781 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0926. Min Act: -0.0000

Data Index: 1191767 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0841. Min Act: -0.0000

Data Index: 917802 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1119289 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1423396 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 1.3061. Min Range: -1.3061

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1127880 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0642. Min Act: -0.0000

Data Index: 217327 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1446919 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1699411 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0326. Min Act: -0.0000

Data Index: 452741 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0200. Min Act: -0.0000

Data Index: 779054 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.3061. Min Range: -1.3061

Max Act: 0.9868. Min Act: -0.0000

Data Index: 684365 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 1.3061. Min Range: -1.3061

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1440936 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1843746 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 1.3061. Min Range: -1.3061

Max Act: 0.9516. Min Act: -0.0000

Data Index: 582386 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 1.3061. Min Range: -1.3061

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1710944 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 1.3061. Min Range: -1.3061

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1992141 (The Pile)

Max Activating Token Index: 339