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

Dataset: The Pile

Neuron 1685 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: 0.8517. Min Range: -0.8517

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1890468 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1858048 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.7791. Min Act: -0.0000

Data Index: 247164 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.6105. Min Act: -0.0000

Data Index: 996714 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1007910 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.5965. Min Act: -0.0000

Data Index: 28646 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1433159 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1679177 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1533813 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4033. Min Act: -0.0000

Data Index: 542194 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1494060 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.3937. Min Act: -0.0000

Data Index: 954436 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1528259 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1401105 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.3801. Min Act: -0.0000

Data Index: 867617 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1184097 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1858962 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1587605 (The Pile)

Max Activating Token Index: 529

Text #18

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.3905. Min Act: -0.0000

Data Index: 378293 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.8517. Min Range: -0.8517

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1597830 (The Pile)

Max Activating Token Index: 329