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

Dataset: The Pile

Neuron 1337 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.9132. Min Act: -0.0000

Data Index: 126752 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1711403 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1148288 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1142777 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1267055 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1848154 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1127163 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7903. Min Act: -0.0000

Data Index: 245225 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1497992 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8196. Min Act: -0.0000

Data Index: 785078 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.8118. Min Act: -0.0000

Data Index: 150586 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1089352 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7519. Min Act: -0.0000

Data Index: 736333 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7117. Min Act: -0.0000

Data Index: 376677 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1815983 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1649388 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7334. Min Act: -0.0000

Data Index: 213321 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.6921. Min Act: -0.0000

Data Index: 421006 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1741852 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.9132. Min Range: -0.9132

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1804664 (The Pile)

Max Activating Token Index: 417