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

Dataset: The Pile

Neuron 3787 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: 0.0106. Min Range: -0.0106

Max Act: 0.0106. Min Act: 0.0000

Data Index: 1487754 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0093. Min Act: -0.0000

Data Index: 361994 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0092. Min Act: -0.0000

Data Index: 1879978 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0090. Min Act: -0.0000

Data Index: 846880 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0089. Min Act: -0.0000

Data Index: 596724 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0088. Min Act: -0.0000

Data Index: 1867830 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0089. Min Act: -0.0000

Data Index: 1976564 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0089. Min Act: -0.0000

Data Index: 1918833 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0087. Min Act: -0.0000

Data Index: 304477 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1546373 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0086. Min Act: -0.0000

Data Index: 275067 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0087. Min Act: -0.0000

Data Index: 889490 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1625731 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0085. Min Act: -0.0000

Data Index: 939940 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0085. Min Act: -0.0000

Data Index: 50937 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1796526 (The Pile)

Max Activating Token Index: 1021

Text #16

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0084. Min Act: -0.0000

Data Index: 333430 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0083. Min Act: -0.0000

Data Index: 604656 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0083. Min Act: -0.0000

Data Index: 396906 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0082. Min Act: -0.0000

Data Index: 399352 (The Pile)

Max Activating Token Index: 1021