Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1021 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1218. Min Act: -0.0001

Data Index: 385502 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1227. Min Act: -0.0001

Data Index: 563140 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1267. Min Act: -0.0001

Data Index: 123167 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1259. Min Act: -0.0001

Data Index: 515621 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1234. Min Act: -0.0001

Data Index: 58083 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1113. Min Act: -0.0001

Data Index: 956891 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1009564 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1140. Min Act: -0.0001

Data Index: 164996 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1094. Min Act: -0.0001

Data Index: 894894 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1034. Min Act: -0.0001

Data Index: 444362 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1202. Min Act: -0.0001

Data Index: 19496 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1108. Min Act: -0.0001

Data Index: 907934 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1152. Min Act: -0.0001

Data Index: 834565 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1135. Min Act: -0.0001

Data Index: 154176 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1090. Min Act: -0.0001

Data Index: 772664 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1067. Min Act: -0.0001

Data Index: 220819 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1034572 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1049. Min Act: -0.0001

Data Index: 474475 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1057. Min Act: -0.0001

Data Index: 627184 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0986. Min Act: -0.0001

Data Index: 41446 (C4 (Web Text))

Max Activating Token Index: 575