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

Dataset: The Pile

Neuron 3142 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0001

Data Index: 487603 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1720861 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1026. Min Act: -0.0001

Data Index: 842662 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1263481 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0878. Min Act: -0.0001

Data Index: 299423 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1855281 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0898. Min Act: -0.0001

Data Index: 330662 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1427956 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0682. Min Act: -0.0001

Data Index: 318985 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0762. Min Act: -0.0001

Data Index: 883086 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0603. Min Act: -0.0001

Data Index: 79007 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0803. Min Act: -0.0001

Data Index: 338807 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0758. Min Act: -0.0001

Data Index: 391317 (The Pile)

Max Activating Token Index: 819

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1491024 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0741. Min Act: -0.0001

Data Index: 765879 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1468119 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1266324 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1849256 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1842108 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0721. Min Act: -0.0001

Data Index: 118808 (The Pile)

Max Activating Token Index: 75