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

Dataset: The Pile

Neuron 144 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: 0.0099. Min Range: -0.0099

Max Act: 0.0099. Min Act: -0.0000

Data Index: 570539 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0096. Min Act: 0.0000

Data Index: 628083 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0000

Data Index: 158522 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0091. Min Act: -0.0000

Data Index: 1324258 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0091. Min Act: -0.0000

Data Index: 1493528 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0090. Min Act: -0.0000

Data Index: 1558667 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0089. Min Act: -0.0000

Data Index: 1117603 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: 0.0000

Data Index: 744726 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0089. Min Act: -0.0000

Data Index: 980436 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0088. Min Act: -0.0000

Data Index: 55211 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0086. Min Act: -0.0000

Data Index: 159932 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0086. Min Act: 0.0000

Data Index: 1575140 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0087. Min Act: -0.0000

Data Index: 1590190 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0000

Data Index: 1708937 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0000

Data Index: 721648 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1545375 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0000

Data Index: 378222 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: -0.0000

Data Index: 146977 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: 0.0000

Data Index: 407475 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0084. Min Act: 0.0000

Data Index: 1708005 (The Pile)

Max Activating Token Index: 1012