Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 517 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1369. Min Act: -0.0003

Data Index: 963020 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1333. Min Act: -0.0003

Data Index: 478016 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1324. Min Act: -0.0003

Data Index: 159763 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1267. Min Act: -0.0003

Data Index: 224594 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1244. Min Act: -0.0003

Data Index: 869858 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1280. Min Act: -0.0003

Data Index: 1003363 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1243. Min Act: -0.0002

Data Index: 693047 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1237. Min Act: -0.0003

Data Index: 377458 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1242. Min Act: -0.0002

Data Index: 171368 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1284. Min Act: -0.0003

Data Index: 1038123 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1226. Min Act: -0.0003

Data Index: 954647 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1222. Min Act: -0.0003

Data Index: 1008521 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1193. Min Act: -0.0002

Data Index: 758697 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1155. Min Act: -0.0003

Data Index: 188093 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1163. Min Act: -0.0003

Data Index: 392413 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1156. Min Act: -0.0003

Data Index: 1207543 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1122. Min Act: -0.0002

Data Index: 907393 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1046. Min Act: -0.0003

Data Index: 747301 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1051. Min Act: -0.0003

Data Index: 1006068 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.1369. Min Range: -0.1369

Max Act: 0.1056. Min Act: -0.0003

Data Index: 1108008 (C4 (Web Text))

Max Activating Token Index: 862