Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2995 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0001

Data Index: 835039 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0955. Min Act: -0.0001

Data Index: 896579 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1059545 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1482719 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0888. Min Act: -0.0001

Data Index: 111340 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0953. Min Act: -0.0001

Data Index: 779625 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1854830 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1043716 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1895598 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0894. Min Act: -0.0001

Data Index: 109844 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0884. Min Act: -0.0001

Data Index: 688737 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0899. Min Act: -0.0001

Data Index: 43203 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0875. Min Act: -0.0001

Data Index: 91938 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1240681 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0871. Min Act: -0.0001

Data Index: 442743 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1292230 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1131234 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0843. Min Act: -0.0001

Data Index: 942625 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1947977 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0840. Min Act: -0.0001

Data Index: 694655 (The Pile)

Max Activating Token Index: 896