Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2008 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1255711 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0218. Min Act: -0.0001

Data Index: 168180 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0205. Min Act: -0.0001

Data Index: 14241 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1208836 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0215. Min Act: -0.0001

Data Index: 203356 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0197. Min Act: -0.0001

Data Index: 282125 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0197. Min Act: -0.0001

Data Index: 221917 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0217. Min Act: -0.0001

Data Index: 934771 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0202. Min Act: -0.0001

Data Index: 420859 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1257886 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1226341 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0188. Min Act: -0.0001

Data Index: 499530 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0194. Min Act: -0.0001

Data Index: 364878 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0185. Min Act: -0.0001

Data Index: 536959 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1025179 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0184. Min Act: -0.0001

Data Index: 8554 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0182. Min Act: -0.0001

Data Index: 744411 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0177. Min Act: -0.0001

Data Index: 701942 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0167. Min Act: -0.0001

Data Index: 177643 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1355172 (C4 (Web Text))

Max Activating Token Index: 865