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

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

Neuron 1482 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1409679 (Python Code)

Max Activating Token Index: 297

Text #1

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1643339 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7714. Min Act: -0.0000

Data Index: 379040 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1370896 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1308670 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1283345 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1377903 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1605910 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1231254 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1567797 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1582140 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.6985. Min Act: -0.0000

Data Index: 354540 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1494232 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1640464 (Python Code)

Max Activating Token Index: 939

Text #14

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1562360 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1470801 (Python Code)

Max Activating Token Index: 710

Text #16

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1611216 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1426655 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1616937 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.6591. Min Act: -0.0000

Data Index: 411697 (C4 (Web Text))

Max Activating Token Index: 285