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

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

Neuron 573 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: 0.1594. Min Range: -0.1594

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1076517 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1355. Min Act: -0.0001

Data Index: 782869 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1195. Min Act: -0.0001

Data Index: 664912 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1241. Min Act: -0.0001

Data Index: 336748 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1060944 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1236. Min Act: -0.0001

Data Index: 102304 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1170. Min Act: -0.0001

Data Index: 422487 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1201263 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1138. Min Act: -0.0001

Data Index: 446769 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1223067 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1132. Min Act: -0.0001

Data Index: 456232 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1066. Min Act: -0.0001

Data Index: 400892 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1131. Min Act: -0.0001

Data Index: 284290 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1307974 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1089831 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0955. Min Act: -0.0001

Data Index: 965874 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1118. Min Act: -0.0001

Data Index: 843329 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1134. Min Act: -0.0001

Data Index: 836598 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1228766 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1104. Min Act: -0.0001

Data Index: 385046 (C4 (Web Text))

Max Activating Token Index: 668