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

Dataset: The Pile

Neuron 2281 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: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0000

Data Index: 1409987 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0124. Min Act: -0.0000

Data Index: 66795 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0000

Data Index: 353344 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0000

Data Index: 1598427 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0000

Data Index: 1498019 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0000

Data Index: 258410 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0000

Data Index: 1357103 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0000

Data Index: 1036125 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0113. Min Act: -0.0000

Data Index: 1432291 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0000

Data Index: 325963 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0000

Data Index: 1286243 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0000

Data Index: 1290527 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0112. Min Act: -0.0000

Data Index: 295187 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0000

Data Index: 1043356 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0000

Data Index: 1922689 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0000

Data Index: 185100 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0000

Data Index: 300216 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0000

Data Index: 1634624 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0000

Data Index: 1021653 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0000

Data Index: 11434 (The Pile)

Max Activating Token Index: 1004