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

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

Neuron 3031 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: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0001

Data Index: 458250 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1316504 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1311. Min Act: -0.0001

Data Index: 214178 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1285. Min Act: -0.0001

Data Index: 454041 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1092412 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1248. Min Act: -0.0001

Data Index: 172013 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1198. Min Act: -0.0001

Data Index: 322092 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1210. Min Act: -0.0001

Data Index: 197479 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1207. Min Act: -0.0001

Data Index: 80582 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1144. Min Act: -0.0001

Data Index: 434665 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1151. Min Act: -0.0001

Data Index: 647834 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1143. Min Act: -0.0001

Data Index: 411299 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1149. Min Act: -0.0001

Data Index: 491448 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1179. Min Act: -0.0001

Data Index: 537185 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1183. Min Act: -0.0001

Data Index: 882302 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1133. Min Act: -0.0001

Data Index: 240016 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1172. Min Act: -0.0001

Data Index: 378166 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1199. Min Act: -0.0001

Data Index: 383305 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1112. Min Act: -0.0001

Data Index: 484244 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1153. Min Act: -0.0001

Data Index: 527034 (C4 (Web Text))

Max Activating Token Index: 155