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

Dataset: The Pile

Neuron 2191 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2259. Min Act: -0.0000

Data Index: 83677 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1522320 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1314. Min Act: -0.0000

Data Index: 980589 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1581987 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1982162 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1304. Min Act: -0.0000

Data Index: 166784 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1261. Min Act: -0.0000

Data Index: 752467 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1721236 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1235. Min Act: -0.0000

Data Index: 21046 (The Pile)

Max Activating Token Index: 249

Text #9

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1200323 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1911041 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1201. Min Act: -0.0000

Data Index: 102304 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1501693 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1522011 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1151. Min Act: -0.0000

Data Index: 314229 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1162. Min Act: -0.0000

Data Index: 189305 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1966708 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1122. Min Act: -0.0000

Data Index: 289317 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1163. Min Act: -0.0000

Data Index: 203443 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1267561 (The Pile)

Max Activating Token Index: 361