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

Dataset: The Pile

Neuron 2937 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: 0.0000

Data Index: 250536 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0764. Min Act: 0.0000

Data Index: 1559383 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0718. Min Act: 0.0000

Data Index: 947860 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1247240 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0648. Min Act: 0.0000

Data Index: 199242 (The Pile)

Max Activating Token Index: 47

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0643. Min Act: -0.0000

Data Index: 830176 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1471656 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1842070 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0634. Min Act: 0.0000

Data Index: 481059 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0654. Min Act: 0.0000

Data Index: 267946 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0627. Min Act: 0.0000

Data Index: 88112 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0622. Min Act: 0.0000

Data Index: 709509 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0620. Min Act: 0.0000

Data Index: 37035 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0607. Min Act: -0.0000

Data Index: 692557 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0606. Min Act: 0.0001

Data Index: 1799957 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0608. Min Act: 0.0000

Data Index: 741825 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0606. Min Act: 0.0001

Data Index: 210562 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0603. Min Act: 0.0000

Data Index: 1798178 (The Pile)

Max Activating Token Index: 116

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0599. Min Act: 0.0000

Data Index: 1094748 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0600. Min Act: 0.0000

Data Index: 686216 (The Pile)

Max Activating Token Index: 88