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

Dataset: The Pile

Neuron 1659 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1597677 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 1.2286. Min Range: -1.2286

Max Act: 1.1619. Min Act: -0.0000

Data Index: 7052 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1295970 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1044827 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1485661 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8661. Min Act: -0.0000

Data Index: 702005 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.8402. Min Act: -0.0000

Data Index: 636792 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6894. Min Act: -0.0000

Data Index: 510423 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7759. Min Act: -0.0000

Data Index: 334485 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1712844 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6162. Min Act: -0.0000

Data Index: 444480 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1864325 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1336498 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1398021 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1526193 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6363. Min Act: -0.0000

Data Index: 882007 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6105. Min Act: -0.0000

Data Index: 662272 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.6168. Min Act: -0.0000

Data Index: 827556 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1694896 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 1.2286. Min Range: -1.2286

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1244451 (The Pile)

Max Activating Token Index: 631