Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 1219 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1637. Min Act: -0.0001

Data Index: 999915 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1443458 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1772031 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1167. Min Act: -0.0000

Data Index: 661566 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1119. Min Act: -0.0000

Data Index: 426148 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1105. Min Act: -0.0000

Data Index: 328331 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1067. Min Act: -0.0001

Data Index: 815407 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1725243 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1054. Min Act: -0.0000

Data Index: 726534 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1046. Min Act: -0.0000

Data Index: 584637 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1878022 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1151915 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1797509 (The Pile)

Max Activating Token Index: 991

Text #13

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1122. Min Act: -0.0001

Data Index: 963665 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1063. Min Act: -0.0001

Data Index: 710017 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1027. Min Act: -0.0000

Data Index: 312768 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1818931 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1812101 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1065. Min Act: -0.0001

Data Index: 677968 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1026. Min Act: -0.0000

Data Index: 144536 (The Pile)

Max Activating Token Index: 379