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

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

Neuron 281 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1293. Min Act: -0.0001

Data Index: 93980 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1164017 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1162. Min Act: -0.0001

Data Index: 138235 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1255. Min Act: -0.0001

Data Index: 977719 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1183. Min Act: -0.0001

Data Index: 965984 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1135. Min Act: -0.0001

Data Index: 775758 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1334038 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1045537 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1139968 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1328893 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1144. Min Act: -0.0001

Data Index: 274392 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1169. Min Act: -0.0001

Data Index: 241836 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1133. Min Act: -0.0001

Data Index: 27342 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1201020 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1148. Min Act: -0.0001

Data Index: 1243683 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1092. Min Act: -0.0001

Data Index: 689203 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1056. Min Act: -0.0001

Data Index: 988257 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1079. Min Act: -0.0001

Data Index: 630738 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1033. Min Act: -0.0001

Data Index: 139548 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1037800 (C4 (Web Text))

Max Activating Token Index: 283