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

Dataset: The Pile

Neuron 373 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: 0.6953. Min Range: -0.6953

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1216768 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6289. Min Act: -0.0000

Data Index: 982935 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6953. Min Act: -0.0000

Data Index: 112692 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6256. Min Act: -0.0000

Data Index: 228530 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5757. Min Act: -0.0000

Data Index: 190315 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.4824. Min Act: -0.0000

Data Index: 98529 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1310201 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5092. Min Act: -0.0000

Data Index: 702415 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1384479 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.4507. Min Act: -0.0000

Data Index: 473925 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1277929 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.4676. Min Act: -0.0000

Data Index: 289031 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.4040. Min Act: -0.0000

Data Index: 1019888 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.3792. Min Act: -0.0000

Data Index: 740481 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.4199. Min Act: -0.0000

Data Index: 530226 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.3869. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.3822. Min Act: -0.0000

Data Index: 611010 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1269625 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1802246 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.3527. Min Act: -0.0000

Data Index: 757461 (The Pile)

Max Activating Token Index: 386