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

Dataset: The Pile

Neuron 2356 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: 0.1355. Min Range: -0.1355

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1297477 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1243. Min Act: -0.0000

Data Index: 597173 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1358408 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1227860 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1152. Min Act: -0.0000

Data Index: 500228 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1138304 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1130. Min Act: -0.0000

Data Index: 484994 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1129. Min Act: -0.0000

Data Index: 169455 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1124. Min Act: -0.0000

Data Index: 304497 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1559780 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1428140 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1351368 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1077. Min Act: -0.0000

Data Index: 629477 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1036533 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1095. Min Act: -0.0000

Data Index: 780194 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1881325 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1771862 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1018651 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1225987 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1018. Min Act: -0.0000

Data Index: 211000 (The Pile)

Max Activating Token Index: 1023