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

Dataset: The Pile

Neuron 4015 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: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0000

Data Index: 887276 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1870369 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1116. Min Act: -0.0000

Data Index: 520314 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1753128 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1921013 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1003. Min Act: -0.0000

Data Index: 449615 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1058590 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0969. Min Act: -0.0000

Data Index: 808950 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0923. Min Act: -0.0000

Data Index: 834129 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0884. Min Act: -0.0000

Data Index: 298491 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0910. Min Act: -0.0000

Data Index: 291445 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1635273 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0898. Min Act: -0.0000

Data Index: 948662 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1441478 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0877. Min Act: -0.0000

Data Index: 426851 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0843. Min Act: -0.0000

Data Index: 685093 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1874180 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1409819 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1028122 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1055344 (The Pile)

Max Activating Token Index: 356