Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 419 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1347. Min Act: -0.0001

Data Index: 370967 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1289. Min Act: -0.0002

Data Index: 52708 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1320. Min Act: -0.0001

Data Index: 325163 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1305. Min Act: -0.0002

Data Index: 834140 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1037162 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1251. Min Act: -0.0001

Data Index: 306249 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1255. Min Act: -0.0002

Data Index: 507868 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1335291 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1198. Min Act: -0.0002

Data Index: 666239 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1109363 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1216. Min Act: -0.0002

Data Index: 519743 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1164792 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1149. Min Act: -0.0002

Data Index: 330812 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1109. Min Act: -0.0002

Data Index: 450832 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1105281 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1097. Min Act: -0.0002

Data Index: 622832 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1127629 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1090. Min Act: -0.0002

Data Index: 424438 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1120. Min Act: -0.0002

Data Index: 813774 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.1347. Min Range: -0.1347

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1038985 (C4 (Web Text))

Max Activating Token Index: 564