Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3129 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.5012. Min Act: 0.0001

Data Index: 1781756 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4762. Min Act: -0.0000

Data Index: 498746 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1778829 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1081663 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4250. Min Act: -0.0000

Data Index: 174414 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1011267 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3998. Min Act: -0.0000

Data Index: 55877 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1693409 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1530653 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1086510 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3940. Min Act: -0.0000

Data Index: 310407 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3678. Min Act: 0.0000

Data Index: 1813161 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1671550 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1472448 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1161130 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1699820 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3757. Min Act: -0.0000

Data Index: 905399 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1096298 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3672. Min Act: 0.0000

Data Index: 320470 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 0.5012. Min Range: -0.5012

Max Act: 0.3745. Min Act: -0.0000

Data Index: 403141 (The Pile)

Max Activating Token Index: 458