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

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

Neuron 440 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0259. Min Act: -0.0000

Data Index: 623554 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0221. Min Act: -0.0000

Data Index: 1211907 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0195. Min Act: -0.0000

Data Index: 1532928 (Python Code)

Max Activating Token Index: 308

Text #3

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0218. Min Act: -0.0000

Data Index: 460467 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0219. Min Act: -0.0000

Data Index: 1349547 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0211. Min Act: -0.0000

Data Index: 335764 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0212. Min Act: -0.0000

Data Index: 633379 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0207. Min Act: -0.0000

Data Index: 345629 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0197. Min Act: -0.0000

Data Index: 1555052 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0202. Min Act: -0.0000

Data Index: 774477 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0202. Min Act: -0.0000

Data Index: 192959 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0211. Min Act: -0.0000

Data Index: 1380529 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0196. Min Act: -0.0000

Data Index: 766643 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0204. Min Act: -0.0000

Data Index: 1398343 (Python Code)

Max Activating Token Index: 976

Text #14

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0195. Min Act: -0.0000

Data Index: 645527 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0190. Min Act: -0.0000

Data Index: 58313 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0197. Min Act: -0.0000

Data Index: 835469 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0187. Min Act: -0.0000

Data Index: 278286 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0195. Min Act: -0.0000

Data Index: 880205 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0259. Min Range: -0.0259

Max Act: 0.0164. Min Act: -0.0000

Data Index: 1608794 (Python Code)

Max Activating Token Index: 601