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

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

Neuron 498 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1238. Min Act: -0.0002

Data Index: 87289 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1170. Min Act: -0.0002

Data Index: 100389 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1159. Min Act: -0.0003

Data Index: 412711 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1010400 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1138. Min Act: -0.0003

Data Index: 584483 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1133. Min Act: -0.0002

Data Index: 211152 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1119. Min Act: -0.0002

Data Index: 612981 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1078. Min Act: -0.0002

Data Index: 141842 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1073. Min Act: -0.0003

Data Index: 104387 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1348146 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1270777 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1106. Min Act: -0.0003

Data Index: 5441 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1110. Min Act: -0.0003

Data Index: 638800 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1107. Min Act: -0.0003

Data Index: 2535 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1135. Min Act: -0.0003

Data Index: 176544 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1100. Min Act: -0.0003

Data Index: 1130380 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1094. Min Act: -0.0003

Data Index: 1177887 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1051. Min Act: -0.0002

Data Index: 578577 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1092. Min Act: -0.0003

Data Index: 44746 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1089. Min Act: -0.0003

Data Index: 1305238 (C4 (Web Text))

Max Activating Token Index: 652