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

Dataset: The Pile

Neuron 2691 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2740. Min Act: -0.0000

Data Index: 212205 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2398. Min Act: -0.0000

Data Index: 979650 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2013. Min Act: -0.0000

Data Index: 918189 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1893. Min Act: -0.0000

Data Index: 503242 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1989. Min Act: -0.0000

Data Index: 83307 (The Pile)

Max Activating Token Index: 379

Text #5

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1302638 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1987. Min Act: -0.0000

Data Index: 615467 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1700. Min Act: -0.0000

Data Index: 570889 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1835. Min Act: -0.0000

Data Index: 16289 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1285087 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2014. Min Act: -0.0000

Data Index: 794602 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1246676 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1415289 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1740. Min Act: -0.0000

Data Index: 687494 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1661. Min Act: -0.0001

Data Index: 1882309 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1102559 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1832. Min Act: -0.0000

Data Index: 712955 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1652. Min Act: -0.0000

Data Index: 866548 (The Pile)

Max Activating Token Index: 527

Text #18

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1286452 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1234081 (The Pile)

Max Activating Token Index: 818