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

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

Neuron 4460 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3719. Min Act: -0.0000

Data Index: 655489 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3729. Min Act: -0.0000

Data Index: 70563 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2996. Min Act: -0.0000

Data Index: 626010 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1092018 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2827. Min Act: -0.0000

Data Index: 26266 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.3025. Min Act: -0.0000

Data Index: 75916 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2677. Min Act: -0.0000

Data Index: 128442 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2773. Min Act: -0.0000

Data Index: 528362 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2696. Min Act: -0.0000

Data Index: 356886 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2678. Min Act: -0.0000

Data Index: 43682 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2515. Min Act: -0.0000

Data Index: 438351 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2274. Min Act: -0.0000

Data Index: 865385 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2429. Min Act: -0.0000

Data Index: 445480 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1170336 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1346971 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2194. Min Act: -0.0000

Data Index: 347980 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1005689 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1064120 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1268316 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.3729. Min Range: -0.3729

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1349330 (C4 (Web Text))

Max Activating Token Index: 471