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

Dataset: The Pile

Neuron 2302 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: 1.0613. Min Range: -1.0613

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1267316 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8714. Min Act: -0.0000

Data Index: 508821 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.9905. Min Act: -0.0000

Data Index: 157289 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1656289 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6778. Min Act: -0.0000

Data Index: 53264 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8979. Min Act: -0.0000

Data Index: 104355 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1770755 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1184633 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1521247 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8392. Min Act: -0.0000

Data Index: 174170 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1535617 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8622. Min Act: -0.0000

Data Index: 390600 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1732017 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1819456 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7900. Min Act: -0.0000

Data Index: 439518 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1430410 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1574567 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1890239 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1055198 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 1.0613. Min Range: -1.0613

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1521851 (The Pile)

Max Activating Token Index: 394