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

Dataset: The Pile

Neuron 1267 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1334898 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0000

Data Index: 466591 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1310. Min Act: -0.0000

Data Index: 323754 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1098581 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1285. Min Act: -0.0000

Data Index: 467690 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1303. Min Act: -0.0000

Data Index: 281007 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1357. Min Act: -0.0000

Data Index: 757358 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1970337 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1293. Min Act: -0.0000

Data Index: 989112 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1281. Min Act: -0.0000

Data Index: 342182 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1188. Min Act: -0.0000

Data Index: 162750 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1962046 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1052718 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1113. Min Act: -0.0000

Data Index: 967662 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1183. Min Act: -0.0000

Data Index: 346133 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1957634 (The Pile)

Max Activating Token Index: 192

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1796876 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1187312 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1165. Min Act: -0.0000

Data Index: 445262 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1109. Min Act: -0.0000

Data Index: 77931 (The Pile)

Max Activating Token Index: 52