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

Dataset: The Pile

Neuron 3977 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: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1323320 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1883718 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1811124 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1215444 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0905. Min Act: -0.0001

Data Index: 712955 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1253244 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1733747 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1180484 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1094859 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1054534 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1611014 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1828704 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1511846 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1398018 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1788323 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0766. Min Act: -0.0001

Data Index: 546282 (The Pile)

Max Activating Token Index: 2

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0661. Min Act: -0.0001

Data Index: 348535 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0743. Min Act: -0.0001

Data Index: 109964 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1244285 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1331941 (The Pile)

Max Activating Token Index: 425