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

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

Neuron 1116 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: 0.1305. Min Range: -0.1305

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1008667 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1249. Min Act: -0.0002

Data Index: 300314 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0002

Data Index: 409119 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1251. Min Act: -0.0002

Data Index: 703687 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1230715 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1236. Min Act: -0.0002

Data Index: 134610 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1149. Min Act: -0.0002

Data Index: 337680 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1183. Min Act: -0.0002

Data Index: 645346 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1097. Min Act: -0.0002

Data Index: 327028 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1168. Min Act: -0.0002

Data Index: 796644 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1178. Min Act: -0.0002

Data Index: 733980 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1163. Min Act: -0.0002

Data Index: 896890 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1119. Min Act: -0.0002

Data Index: 580052 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1154. Min Act: -0.0002

Data Index: 142860 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1194. Min Act: -0.0002

Data Index: 218959 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1168. Min Act: -0.0002

Data Index: 960068 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1146. Min Act: -0.0002

Data Index: 816542 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1119. Min Act: -0.0002

Data Index: 803118 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1120. Min Act: -0.0002

Data Index: 529979 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1170. Min Act: -0.0002

Data Index: 802038 (C4 (Web Text))

Max Activating Token Index: 120