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

Dataset: The Pile

Neuron 4719 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: 1.5851. Min Range: -1.5851

Max Act: 1.4265. Min Act: -0.0000

Data Index: 1424735 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5851. Min Act: -0.0000

Data Index: 751452 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.4115. Min Act: -0.0000

Data Index: 1167212 (The Pile)

Max Activating Token Index: 524

Text #3

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.3489. Min Act: -0.0000

Data Index: 745652 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5323. Min Act: -0.0000

Data Index: 1459883 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1560162 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1074279 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1456550 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0794. Min Act: -0.0000

Data Index: 723912 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.2804. Min Act: -0.0000

Data Index: 955300 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.9754. Min Act: -0.0000

Data Index: 172437 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1296933 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.0503. Min Act: -0.0000

Data Index: 348866 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1810211 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1771045 (The Pile)

Max Activating Token Index: 156

Text #15

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1514385 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.9116. Min Act: -0.0000

Data Index: 167617 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.9679. Min Act: -0.0001

Data Index: 1442559 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1148427 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.5851. Min Range: -1.5851

Max Act: 0.5565. Min Act: -0.0000

Data Index: 591862 (The Pile)

Max Activating Token Index: 891