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

Dataset: The Pile

Neuron 2084 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: 0.1221. Min Range: -0.1221

Max Act: 0.1181. Min Act: 0.0000

Data Index: 1836205 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1177. Min Act: 0.0000

Data Index: 1593340 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: 0.0000

Data Index: 404826 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1169. Min Act: 0.0000

Data Index: 1798377 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1173. Min Act: 0.0000

Data Index: 1347998 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1170. Min Act: 0.0000

Data Index: 655168 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1165. Min Act: 0.0000

Data Index: 1806699 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1166. Min Act: 0.0000

Data Index: 531348 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1199. Min Act: 0.0000

Data Index: 51485 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1158. Min Act: 0.0000

Data Index: 786880 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1151. Min Act: 0.0000

Data Index: 1871390 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1149. Min Act: 0.0000

Data Index: 1500644 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1191. Min Act: 0.0000

Data Index: 680058 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1142. Min Act: 0.0000

Data Index: 362874 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1176. Min Act: 0.0000

Data Index: 710879 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1131. Min Act: 0.0000

Data Index: 794011 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1130. Min Act: 0.0000

Data Index: 448962 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1117. Min Act: 0.0000

Data Index: 1563224 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1112. Min Act: 0.0000

Data Index: 434007 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1106. Min Act: 0.0000

Data Index: 223717 (The Pile)

Max Activating Token Index: 1023