Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1401738 (Python Code)

Max Activating Token Index: 194

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1245718 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0206. Min Act: -0.0006

Data Index: 624516 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1388840 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1401579 (Python Code)

Max Activating Token Index: 890

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1390557 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1394708 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1106532 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0186. Min Act: -0.0006

Data Index: 301203 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1393099 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1591170 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1646495 (Python Code)

Max Activating Token Index: 630

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0178. Min Act: -0.0006

Data Index: 1361223 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1547087 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1110530 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1535313 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1420262 (Python Code)

Max Activating Token Index: 960

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1496226 (Python Code)

Max Activating Token Index: 443

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1531307 (Python Code)

Max Activating Token Index: 328

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1412106 (Python Code)

Max Activating Token Index: 971