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

Dataset: The Pile

Neuron 4263 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: 4.3047. Min Range: -4.3047

Max Act: 4.3047. Min Act: -0.0000

Data Index: 530794 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.7388. Min Act: -0.0000

Data Index: 1518513 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.5557. Min Act: -0.0000

Data Index: 1717200 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.6642. Min Act: -0.0000

Data Index: 633382 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.3498. Min Act: -0.0000

Data Index: 1614675 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.4272. Min Act: -0.0000

Data Index: 1294439 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.4178. Min Act: -0.0000

Data Index: 1559296 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.5749. Min Act: -0.0000

Data Index: 766346 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.2525. Min Act: -0.0000

Data Index: 1192060 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.4001. Min Act: -0.0000

Data Index: 453248 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.1909. Min Act: -0.0000

Data Index: 1567126 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.3419. Min Act: -0.0000

Data Index: 1198174 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.1484. Min Act: -0.0000

Data Index: 718766 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.3158. Min Act: -0.0000

Data Index: 1382633 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.1212. Min Act: -0.0000

Data Index: 1195745 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.4396. Min Act: -0.0000

Data Index: 556994 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.1341. Min Act: -0.0000

Data Index: 1889994 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.5555. Min Act: -0.0000

Data Index: 1488183 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.0779. Min Act: -0.0000

Data Index: 1691373 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 4.3047. Min Range: -4.3047

Max Act: 3.2274. Min Act: -0.0000

Data Index: 754272 (The Pile)

Max Activating Token Index: 4