Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 958 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1202. Min Act: -0.0006

Data Index: 1099800 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0005

Data Index: 780010 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1144. Min Act: -0.0006

Data Index: 1097946 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1144. Min Act: -0.0006

Data Index: 352537 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1155. Min Act: -0.0006

Data Index: 1253388 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1069. Min Act: -0.0006

Data Index: 11755 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1098. Min Act: -0.0006

Data Index: 828733 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1128. Min Act: -0.0006

Data Index: 757071 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1123. Min Act: -0.0006

Data Index: 878401 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1006. Min Act: -0.0006

Data Index: 294850 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1125. Min Act: -0.0005

Data Index: 1094093 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1112. Min Act: -0.0006

Data Index: 117355 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1106. Min Act: -0.0006

Data Index: 473490 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1051. Min Act: -0.0005

Data Index: 872548 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1127. Min Act: -0.0005

Data Index: 810085 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1042. Min Act: -0.0006

Data Index: 589219 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1073. Min Act: -0.0005

Data Index: 627442 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1116. Min Act: -0.0005

Data Index: 522112 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1068. Min Act: -0.0005

Data Index: 794063 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1027. Min Act: -0.0006

Data Index: 963655 (C4 (Web Text))

Max Activating Token Index: 597