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

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

Neuron 3173 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: 1.6243. Min Range: -1.6243

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1585082 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.4452. Min Act: -0.0000

Data Index: 1655501 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.3976. Min Act: -0.0000

Data Index: 729755 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1416813 (Python Code)

Max Activating Token Index: 606

Text #4

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.2154. Min Act: -0.0000

Data Index: 45265 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1431626 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1449571 (Python Code)

Max Activating Token Index: 583

Text #7

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0971. Min Act: -0.0000

Data Index: 535199 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.1012. Min Act: -0.0000

Data Index: 1527887 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1377870 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1504546 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1590114 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.2182. Min Act: -0.0000

Data Index: 494583 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1649777 (Python Code)

Max Activating Token Index: 421

Text #14

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1393996 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1473162 (Python Code)

Max Activating Token Index: 88

Text #16

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1575589 (Python Code)

Max Activating Token Index: 661

Text #17

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0630. Min Act: -0.0000

Data Index: 307641 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.6243. Min Range: -1.6243

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1413752 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 1.6243. Min Range: -1.6243

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1572583 (Python Code)

Max Activating Token Index: 569