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

Dataset: The Pile

Neuron 1536 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: 0.7357. Min Range: -0.7357

Max Act: 0.7357. Min Act: -0.0000

Data Index: 627756 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1021333 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1333588 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6218. Min Act: 0.0000

Data Index: 1812526 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1835712 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5999. Min Act: -0.0000

Data Index: 949972 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5681. Min Act: 0.0000

Data Index: 1787797 (The Pile)

Max Activating Token Index: 793

Text #7

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5768. Min Act: 0.0000

Data Index: 1018342 (The Pile)

Max Activating Token Index: 868

Text #8

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1899369 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1123911 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1042270 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1697123 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5125. Min Act: 0.0000

Data Index: 1944771 (The Pile)

Max Activating Token Index: 623

Text #13

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1763462 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5578. Min Act: -0.0000

Data Index: 398145 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5274. Min Act: 0.0000

Data Index: 1151736 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5230. Min Act: -0.0000

Data Index: 400044 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1954175 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1764784 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1965382 (The Pile)

Max Activating Token Index: 427