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

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

Neuron 150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1501. Min Act: -0.0002

Data Index: 138454 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1437. Min Act: -0.0002

Data Index: 427351 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1296. Min Act: -0.0002

Data Index: 370196 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1343. Min Act: -0.0002

Data Index: 433777 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1264. Min Act: -0.0002

Data Index: 1143057 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1212. Min Act: -0.0002

Data Index: 1145637 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1225. Min Act: -0.0002

Data Index: 140843 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1258. Min Act: -0.0002

Data Index: 715372 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1187. Min Act: -0.0002

Data Index: 951033 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1011791 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1163. Min Act: -0.0002

Data Index: 782220 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1155. Min Act: -0.0002

Data Index: 152190 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1236. Min Act: -0.0002

Data Index: 277012 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1190. Min Act: -0.0002

Data Index: 684575 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1127. Min Act: -0.0002

Data Index: 927227 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1092. Min Act: -0.0002

Data Index: 938481 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1089. Min Act: -0.0002

Data Index: 317372 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1063. Min Act: -0.0002

Data Index: 505315 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1002. Min Act: -0.0002

Data Index: 816200 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1116621 (C4 (Web Text))

Max Activating Token Index: 776