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

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

Neuron 431 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0001

Data Index: 778461 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1177. Min Act: -0.0001

Data Index: 850622 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1155. Min Act: -0.0001

Data Index: 701271 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1286. Min Act: -0.0001

Data Index: 453122 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1214419 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1179. Min Act: -0.0001

Data Index: 901118 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1212. Min Act: -0.0001

Data Index: 780969 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1101690 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1106. Min Act: -0.0001

Data Index: 211973 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1133. Min Act: -0.0001

Data Index: 812004 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1166. Min Act: -0.0001

Data Index: 984091 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1018529 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1106. Min Act: -0.0001

Data Index: 790690 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1167. Min Act: -0.0001

Data Index: 436736 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1132. Min Act: -0.0001

Data Index: 180461 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1101. Min Act: -0.0001

Data Index: 828450 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1012. Min Act: -0.0001

Data Index: 53292 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1119. Min Act: -0.0001

Data Index: 564263 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1068. Min Act: -0.0001

Data Index: 412972 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1268119 (C4 (Web Text))

Max Activating Token Index: 639