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

Dataset: The Pile

Neuron 441 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: 0.8339. Min Range: -0.8339

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1236167 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.8079. Min Act: -0.0000

Data Index: 909618 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1189108 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1852200 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1068463 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.7096. Min Act: -0.0000

Data Index: 305182 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6311. Min Act: 0.0000

Data Index: 708072 (The Pile)

Max Activating Token Index: 933

Text #7

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1538921 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5398. Min Act: 0.0000

Data Index: 492777 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1378895 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5675. Min Act: -0.0000

Data Index: 566658 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5881. Min Act: -0.0000

Data Index: 314643 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1536410 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1854374 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5012. Min Act: -0.0000

Data Index: 723248 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5114. Min Act: -0.0000

Data Index: 891025 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1856234 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1595157 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1338599 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 0.8339. Min Range: -0.8339

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1095039 (The Pile)

Max Activating Token Index: 351