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

Dataset: The Pile

Neuron 1561 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: 0.1527. Min Range: -0.1527

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1715792 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1403. Min Act: -0.0000

Data Index: 792630 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1308084 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1634574 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1212. Min Act: -0.0000

Data Index: 630839 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1938749 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1219. Min Act: -0.0000

Data Index: 578778 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1660693 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1093. Min Act: -0.0000

Data Index: 494825 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1051. Min Act: -0.0000

Data Index: 277060 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1185. Min Act: -0.0000

Data Index: 216172 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1333113 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1120. Min Act: -0.0000

Data Index: 582861 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1753183 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1261055 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1083. Min Act: -0.0000

Data Index: 979909 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1037. Min Act: -0.0000

Data Index: 111585 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1693615 (The Pile)

Max Activating Token Index: 264

Text #18

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1280426 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.1527. Min Range: -0.1527

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1012482 (The Pile)

Max Activating Token Index: 84