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

Dataset: The Pile

Neuron 3081 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: 0.0182. Min Range: -0.0182

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1556816 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0163. Min Act: -0.0000

Data Index: 787988 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0157. Min Act: -0.0000

Data Index: 628741 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0142. Min Act: -0.0000

Data Index: 830511 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0146. Min Act: -0.0000

Data Index: 1711650 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0139. Min Act: -0.0000

Data Index: 1693591 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0138. Min Act: -0.0000

Data Index: 726107 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0135. Min Act: -0.0000

Data Index: 560302 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0133. Min Act: -0.0000

Data Index: 1048355 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0132. Min Act: -0.0000

Data Index: 1922889 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1359605 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0131. Min Act: -0.0000

Data Index: 1621717 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0129. Min Act: -0.0000

Data Index: 505345 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0129. Min Act: -0.0000

Data Index: 445593 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0127. Min Act: -0.0000

Data Index: 1621405 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0126. Min Act: -0.0000

Data Index: 51677 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0124. Min Act: -0.0000

Data Index: 1838782 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1616084 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0124. Min Act: -0.0000

Data Index: 219296 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0182. Min Range: -0.0182

Max Act: 0.0124. Min Act: -0.0000

Data Index: 219974 (The Pile)

Max Activating Token Index: 840