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

Dataset: The Pile

Neuron 569 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: 0.1439. Min Range: -0.1439

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1592754 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1316. Min Act: 0.0000

Data Index: 203318 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1289. Min Act: -0.0000

Data Index: 573104 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1279. Min Act: -0.0000

Data Index: 480038 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1244. Min Act: 0.0000

Data Index: 622193 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1223. Min Act: -0.0000

Data Index: 426008 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1205. Min Act: 0.0000

Data Index: 960415 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1190. Min Act: -0.0000

Data Index: 817288 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1500835 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1168. Min Act: -0.0000

Data Index: 518096 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1111044 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1154. Min Act: -0.0000

Data Index: 798387 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1138. Min Act: -0.0000

Data Index: 952004 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1130. Min Act: -0.0000

Data Index: 377900 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1131. Min Act: -0.0000

Data Index: 823382 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1129. Min Act: -0.0000

Data Index: 606760 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1851731 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1141748 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1530690 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1440447 (The Pile)

Max Activating Token Index: 431