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

Dataset: The Pile

Neuron 1721 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: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0000

Data Index: 281809 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0125. Min Act: -0.0000

Data Index: 936156 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0125. Min Act: 0.0000

Data Index: 575607 (The Pile)

Max Activating Token Index: 991

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0125. Min Act: -0.0000

Data Index: 612319 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0124. Min Act: 0.0000

Data Index: 1636953 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0000

Data Index: 250717 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0129. Min Act: -0.0000

Data Index: 446912 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1129817 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1599212 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0000

Data Index: 1403404 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0000

Data Index: 788887 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0000

Data Index: 745124 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0122. Min Act: 0.0000

Data Index: 250683 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0122. Min Act: -0.0000

Data Index: 65002 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0000

Data Index: 1113726 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0000

Data Index: 162382 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0000

Data Index: 1998318 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0120. Min Act: -0.0000

Data Index: 810010 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0000

Data Index: 771369 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0000

Data Index: 1372948 (The Pile)

Max Activating Token Index: 1016