Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2248 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1232185 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2509. Min Act: 0.0000

Data Index: 154403 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2371. Min Act: -0.0000

Data Index: 52590 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1290316 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2472. Min Act: -0.0000

Data Index: 321605 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2222. Min Act: -0.0000

Data Index: 55715 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2299. Min Act: -0.0000

Data Index: 333549 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2168. Min Act: -0.0000

Data Index: 589491 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2207. Min Act: 0.0000

Data Index: 590803 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2201. Min Act: -0.0000

Data Index: 266264 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2193. Min Act: -0.0000

Data Index: 9434 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1010867 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2136. Min Act: -0.0000

Data Index: 498128 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2176. Min Act: 0.0000

Data Index: 725334 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2092. Min Act: -0.0000

Data Index: 668526 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1227823 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2147. Min Act: 0.0000

Data Index: 454257 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2009. Min Act: -0.0000

Data Index: 863407 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2136. Min Act: -0.0000

Data Index: 751600 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2057. Min Act: 0.0000

Data Index: 481657 (C4 (Web Text))

Max Activating Token Index: 275