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

Dataset: The Pile

Neuron 385 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: 0.1336. Min Range: -0.1336

Max Act: 0.1336. Min Act: 0.0000

Data Index: 1455843 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1294. Min Act: 0.0000

Data Index: 1659088 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1258. Min Act: -0.0000

Data Index: 872517 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1220. Min Act: 0.0000

Data Index: 1989898 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1214. Min Act: 0.0000

Data Index: 119121 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1246. Min Act: 0.0000

Data Index: 393335 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1174. Min Act: 0.0000

Data Index: 490201 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1154. Min Act: 0.0000

Data Index: 1476190 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1149. Min Act: 0.0000

Data Index: 341311 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1147. Min Act: -0.0000

Data Index: 227108 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1141. Min Act: 0.0000

Data Index: 801573 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1167. Min Act: -0.0000

Data Index: 663216 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1121. Min Act: 0.0000

Data Index: 1021904 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1109. Min Act: 0.0000

Data Index: 124426 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1146. Min Act: 0.0000

Data Index: 1729262 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1105. Min Act: 0.0000

Data Index: 433278 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1096. Min Act: 0.0000

Data Index: 1914513 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1135. Min Act: 0.0000

Data Index: 1762930 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1093. Min Act: 0.0000

Data Index: 1445349 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1087. Min Act: 0.0000

Data Index: 444469 (The Pile)

Max Activating Token Index: 132