Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3626 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1323. Min Act: -0.0001

Data Index: 964735 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1210. Min Act: -0.0001

Data Index: 372359 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1479316 (Python Code)

Max Activating Token Index: 871

Text #3

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1251. Min Act: -0.0001

Data Index: 585448 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1513985 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1495510 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1622704 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1326550 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1048. Min Act: -0.0001

Data Index: 910057 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1572099 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1045. Min Act: -0.0001

Data Index: 328710 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0998. Min Act: -0.0001

Data Index: 454850 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1061924 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1384270 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1040206 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0925. Min Act: -0.0001

Data Index: 725114 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1523690 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0894. Min Act: -0.0001

Data Index: 2445 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1498367 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0859. Min Act: -0.0001

Data Index: 73327 (C4 (Web Text))

Max Activating Token Index: 322