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

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

Neuron 3642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1650. Min Act: -0.0000

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1260. Min Act: -0.0000

Data Index: 29082 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1103874 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1159. Min Act: -0.0000

Data Index: 854774 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1155. Min Act: -0.0000

Data Index: 66174 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1172318 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1170. Min Act: -0.0000

Data Index: 423639 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1131. Min Act: -0.0000

Data Index: 475910 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1165. Min Act: -0.0000

Data Index: 783250 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1246604 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1186. Min Act: -0.0000

Data Index: 487467 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1090. Min Act: -0.0000

Data Index: 211772 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1075107 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1112. Min Act: -0.0000

Data Index: 109301 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1287038 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1229362 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1090341 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1033. Min Act: -0.0000

Data Index: 538564 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1067. Min Act: -0.0000

Data Index: 973082 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1022. Min Act: -0.0000

Data Index: 286378 (C4 (Web Text))

Max Activating Token Index: 826