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

Dataset: The Pile

Neuron 986 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.7238. Min Act: -0.0000

Data Index: 688624 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1496329 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1408398 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6849. Min Act: -0.0000

Data Index: 362484 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1158730 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5962. Min Act: -0.0000

Data Index: 27304 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6286. Min Act: -0.0000

Data Index: 345254 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1168885 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1421447 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1360460 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6097. Min Act: -0.0000

Data Index: 44230 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5548. Min Act: -0.0000

Data Index: 332351 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1394558 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5854. Min Act: -0.0000

Data Index: 858212 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1524527 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6045. Min Act: -0.0000

Data Index: 106100 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1870416 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1951835 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5577. Min Act: -0.0000

Data Index: 301683 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 0.7238. Min Range: -0.7238

Max Act: 0.5932. Min Act: -0.0000

Data Index: 336252 (The Pile)

Max Activating Token Index: 588