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

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

Neuron 4097 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2420. Min Act: -0.0002

Data Index: 786219 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2032. Min Act: -0.0002

Data Index: 271033 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2365. Min Act: -0.0002

Data Index: 702828 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2325. Min Act: -0.0002

Data Index: 325663 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2283. Min Act: -0.0002

Data Index: 450799 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2268. Min Act: -0.0002

Data Index: 327252 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2351. Min Act: -0.0002

Data Index: 1010741 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2375. Min Act: -0.0002

Data Index: 363404 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2124. Min Act: -0.0002

Data Index: 1245215 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2047. Min Act: -0.0002

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1041899 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2263. Min Act: -0.0002

Data Index: 454293 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2047. Min Act: -0.0002

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2068. Min Act: -0.0002

Data Index: 300823 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2081. Min Act: -0.0002

Data Index: 45151 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2150. Min Act: -0.0002

Data Index: 1329631 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2130. Min Act: -0.0002

Data Index: 351807 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2169. Min Act: -0.0002

Data Index: 1155110 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2118. Min Act: -0.0002

Data Index: 1020440 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.2420. Min Range: -0.2420

Max Act: 0.2039. Min Act: -0.0002

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 791