Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3414 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1249. Min Act: -0.0001

Data Index: 362998 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1304061 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1171. Min Act: -0.0001

Data Index: 815182 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1198. Min Act: -0.0001

Data Index: 629384 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1246. Min Act: -0.0001

Data Index: 837040 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1094222 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1181. Min Act: -0.0001

Data Index: 82857 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1197. Min Act: -0.0001

Data Index: 388898 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1162. Min Act: -0.0001

Data Index: 231143 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1201. Min Act: -0.0001

Data Index: 687665 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1111. Min Act: -0.0001

Data Index: 22849 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1140. Min Act: -0.0001

Data Index: 556480 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1100263 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1160. Min Act: -0.0001

Data Index: 461114 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1035186 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1111. Min Act: -0.0001

Data Index: 799185 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1094. Min Act: -0.0001

Data Index: 664781 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1139. Min Act: -0.0001

Data Index: 276155 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1053. Min Act: -0.0001

Data Index: 897842 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1318063 (C4 (Web Text))

Max Activating Token Index: 113