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

Dataset: The Pile

Neuron 3221 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1690374 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4594. Min Act: -0.0000

Data Index: 172191 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1563672 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1756000 (The Pile)

Max Activating Token Index: 747

Text #4

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4767. Min Act: -0.0000

Data Index: 442784 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4248. Min Act: -0.0000

Data Index: 230392 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1049773 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1118950 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4569. Min Act: -0.0000

Data Index: 763318 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1474643 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1177249 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1782494 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1993814 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1811726 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.4364. Min Act: -0.0000

Data Index: 423862 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1687454 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1338856 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1748108 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1804713 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1533147 (The Pile)

Max Activating Token Index: 244