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

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

Neuron 916 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1494. Min Act: -0.0002

Data Index: 579730 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1402. Min Act: -0.0002

Data Index: 451632 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1476. Min Act: -0.0002

Data Index: 381640 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1558. Min Act: -0.0002

Data Index: 915496 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1129808 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1226. Min Act: -0.0002

Data Index: 798440 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1243. Min Act: -0.0002

Data Index: 318133 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1323250 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1131. Min Act: -0.0002

Data Index: 242390 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1130. Min Act: -0.0002

Data Index: 712232 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1127. Min Act: -0.0002

Data Index: 43398 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1255. Min Act: -0.0002

Data Index: 737254 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1074. Min Act: -0.0002

Data Index: 226271 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1079. Min Act: -0.0002

Data Index: 194953 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1065. Min Act: -0.0002

Data Index: 316564 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0989. Min Act: -0.0002

Data Index: 7011 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1206. Min Act: -0.0002

Data Index: 845898 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1051. Min Act: -0.0002

Data Index: 716644 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1018553 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0956. Min Act: -0.0002

Data Index: 368889 (C4 (Web Text))

Max Activating Token Index: 29