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

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

Neuron 219 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1215443 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1161. Min Act: -0.0001

Data Index: 36836 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1218014 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1297. Min Act: -0.0001

Data Index: 699933 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1330. Min Act: -0.0001

Data Index: 832306 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1268. Min Act: -0.0002

Data Index: 826670 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1219. Min Act: -0.0001

Data Index: 296009 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1228. Min Act: -0.0001

Data Index: 242206 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1361. Min Act: -0.0001

Data Index: 499655 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1073. Min Act: -0.0001

Data Index: 98180 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1046. Min Act: -0.0001

Data Index: 218421 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1160. Min Act: -0.0001

Data Index: 67812 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1168185 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1324513 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1128. Min Act: -0.0001

Data Index: 820367 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1139486 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1114. Min Act: -0.0001

Data Index: 805567 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1057. Min Act: -0.0001

Data Index: 875480 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.0875. Min Act: -0.0001

Data Index: 178911 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.1476. Min Range: -0.1476

Max Act: 0.1066. Min Act: -0.0001

Data Index: 633219 (C4 (Web Text))

Max Activating Token Index: 405