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

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

Neuron 2658 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1008782 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1326517 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1349220 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1198041 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1224. Min Act: -0.0001

Data Index: 842503 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1205. Min Act: -0.0001

Data Index: 833785 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1189. Min Act: -0.0001

Data Index: 295177 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1223. Min Act: -0.0001

Data Index: 401707 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1315795 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1129. Min Act: -0.0001

Data Index: 238455 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1195174 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1137. Min Act: -0.0001

Data Index: 973157 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1133. Min Act: -0.0001

Data Index: 972142 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1092. Min Act: -0.0001

Data Index: 983181 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1082210 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1073. Min Act: -0.0001

Data Index: 750919 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1089851 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1034. Min Act: -0.0001

Data Index: 968244 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1032. Min Act: -0.0001

Data Index: 871686 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0989. Min Act: -0.0001

Data Index: 760033 (C4 (Web Text))

Max Activating Token Index: 846