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

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

Neuron 2153 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: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0001

Data Index: 621336 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1094659 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1388. Min Act: -0.0001

Data Index: 636760 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1156047 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1265. Min Act: -0.0001

Data Index: 415171 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1274. Min Act: -0.0001

Data Index: 921410 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1119407 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1352768 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1402. Min Act: -0.0001

Data Index: 752534 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1105512 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1231382 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1080. Min Act: -0.0001

Data Index: 521358 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1133. Min Act: -0.0001

Data Index: 352120 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1126. Min Act: -0.0001

Data Index: 187590 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1262694 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1113. Min Act: -0.0001

Data Index: 299323 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1128. Min Act: -0.0001

Data Index: 811687 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1146324 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1069. Min Act: -0.0001

Data Index: 9370 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1161308 (C4 (Web Text))

Max Activating Token Index: 52