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

Dataset: The Pile

Neuron 862 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.7224. Min Act: -0.0000

Data Index: 582125 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6293. Min Act: -0.0000

Data Index: 44160 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6145. Min Act: -0.0000

Data Index: 914370 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1802486 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1832326 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6146. Min Act: -0.0000

Data Index: 256130 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1281568 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6225. Min Act: -0.0000

Data Index: 978421 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1042657 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6201. Min Act: -0.0000

Data Index: 343109 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1501859 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5758. Min Act: -0.0000

Data Index: 712764 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5895. Min Act: -0.0000

Data Index: 572108 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5799. Min Act: -0.0000

Data Index: 957341 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5563. Min Act: -0.0000

Data Index: 940734 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1770357 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5677. Min Act: -0.0000

Data Index: 565402 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5810. Min Act: -0.0000

Data Index: 448962 (The Pile)

Max Activating Token Index: 979

Text #18

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5588. Min Act: -0.0000

Data Index: 435712 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1750648 (The Pile)

Max Activating Token Index: 893