Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3428 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0142. Min Act: -0.0000

Data Index: 1858840 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0138. Min Act: -0.0000

Data Index: 1173294 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0136. Min Act: -0.0000

Data Index: 1009454 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0127. Min Act: -0.0000

Data Index: 269118 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0128. Min Act: -0.0001

Data Index: 885808 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0118. Min Act: -0.0000

Data Index: 396961 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0117. Min Act: -0.0000

Data Index: 1836612 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0116. Min Act: -0.0000

Data Index: 960655 (The Pile)

Max Activating Token Index: 985

Text #8

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0118. Min Act: -0.0000

Data Index: 72599 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0114. Min Act: -0.0000

Data Index: 888808 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0114. Min Act: -0.0001

Data Index: 193970 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0114. Min Act: -0.0000

Data Index: 1326729 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0114. Min Act: -0.0000

Data Index: 256550 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0116. Min Act: -0.0000

Data Index: 1322064 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0114. Min Act: -0.0000

Data Index: 1307176 (The Pile)

Max Activating Token Index: 902

Text #15

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0113. Min Act: -0.0001

Data Index: 635897 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0114. Min Act: -0.0000

Data Index: 1477426 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0112. Min Act: -0.0000

Data Index: 473646 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0000

Data Index: 554147 (The Pile)

Max Activating Token Index: 955

Text #19

Max Range: 0.0142. Min Range: -0.0142

Max Act: 0.0111. Min Act: -0.0001

Data Index: 765549 (The Pile)

Max Activating Token Index: 1003