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

Dataset: The Pile

Neuron 3410 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.1266. Min Act: -0.0000

Data Index: 1158671 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0378. Min Act: 0.0000

Data Index: 1700885 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9467. Min Act: -0.0000

Data Index: 216939 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9314. Min Act: -0.0000

Data Index: 196851 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1251737 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8827. Min Act: -0.0000

Data Index: 363958 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9589. Min Act: -0.0000

Data Index: 806877 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1419188 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1030153 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7701. Min Act: -0.0000

Data Index: 231549 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8146. Min Act: -0.0000

Data Index: 275623 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1695672 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8411. Min Act: 0.0000

Data Index: 104406 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7796. Min Act: -0.0000

Data Index: 712943 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7770. Min Act: -0.0000

Data Index: 594085 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1425354 (The Pile)

Max Activating Token Index: 802

Text #16

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7849. Min Act: -0.0000

Data Index: 388099 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1625189 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7652. Min Act: -0.0000

Data Index: 308357 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7387. Min Act: 0.0000

Data Index: 1912565 (The Pile)

Max Activating Token Index: 1005