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

Dataset: The Pile

Neuron 61 in Layer 1

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: -0.0003

Data Index: 430638 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1042. Min Act: -0.0003

Data Index: 936084 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1001. Min Act: -0.0003

Data Index: 1583050 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1028. Min Act: -0.0003

Data Index: 1058789 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0981. Min Act: -0.0003

Data Index: 625148 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0947. Min Act: -0.0003

Data Index: 1843360 (The Pile)

Max Activating Token Index: 220

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0941. Min Act: -0.0003

Data Index: 984555 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0903. Min Act: -0.0003

Data Index: 445537 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0958. Min Act: -0.0003

Data Index: 1981752 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0921. Min Act: -0.0003

Data Index: 1293458 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0916. Min Act: -0.0003

Data Index: 906452 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1006676 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0908. Min Act: -0.0003

Data Index: 675099 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1558784 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0846. Min Act: -0.0003

Data Index: 1069411 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0855. Min Act: -0.0003

Data Index: 1241814 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0798. Min Act: -0.0003

Data Index: 1952640 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1530366 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0817. Min Act: -0.0003

Data Index: 1958878 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1593041 (The Pile)

Max Activating Token Index: 227