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

Dataset: The Pile

Neuron 387 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: 0.1320. Min Range: -0.1320

Max Act: 0.1320. Min Act: -0.0000

Data Index: 902320 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1263. Min Act: 0.0000

Data Index: 746876 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1520108 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1193. Min Act: 0.0000

Data Index: 149813 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1162. Min Act: -0.0000

Data Index: 524930 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1335340 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1144. Min Act: 0.0000

Data Index: 259390 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1620385 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1143. Min Act: 0.0000

Data Index: 74537 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1821655 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1139. Min Act: -0.0000

Data Index: 314940 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1118. Min Act: 0.0000

Data Index: 884879 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1092. Min Act: -0.0000

Data Index: 138196 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1567531 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1085. Min Act: 0.0000

Data Index: 1843714 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1064. Min Act: 0.0000

Data Index: 137153 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1048. Min Act: 0.0000

Data Index: 1410182 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1045. Min Act: -0.0000

Data Index: 304096 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1031. Min Act: 0.0000

Data Index: 476640 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1320. Min Range: -0.1320

Max Act: 0.1032. Min Act: 0.0000

Data Index: 1736079 (The Pile)

Max Activating Token Index: 1023