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

Dataset: The Pile

Neuron 163 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: 1.2679. Min Range: -1.2679

Max Act: 1.2679. Min Act: -0.0000

Data Index: 98874 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 1.2679. Min Range: -1.2679

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1770495 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 1.2679. Min Range: -1.2679

Max Act: 1.0107. Min Act: -0.0000

Data Index: 602392 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.8968. Min Act: 0.0000

Data Index: 115302 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1700135 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7517. Min Act: 0.0000

Data Index: 1323096 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.8395. Min Act: 0.0000

Data Index: 1738844 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7859. Min Act: -0.0000

Data Index: 626066 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7863. Min Act: -0.0000

Data Index: 902054 (The Pile)

Max Activating Token Index: 152

Text #9

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1135531 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1377722 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1973080 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1741523 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7395. Min Act: -0.0000

Data Index: 635459 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7317. Min Act: -0.0000

Data Index: 589042 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.7873. Min Act: -0.0000

Data Index: 130735 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.6676. Min Act: -0.0000

Data Index: 724690 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.6488. Min Act: -0.0000

Data Index: 353949 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1483633 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 1.2679. Min Range: -1.2679

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1914357 (The Pile)

Max Activating Token Index: 202