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

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

Neuron 392 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1480457 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1163418 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2836. Min Act: -0.0000

Data Index: 223625 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2521. Min Act: -0.0000

Data Index: 931993 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2370. Min Act: -0.0000

Data Index: 475012 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1148361 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2274. Min Act: -0.0000

Data Index: 453389 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2107. Min Act: -0.0000

Data Index: 430773 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2233. Min Act: -0.0000

Data Index: 147105 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1002397 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2049. Min Act: -0.0000

Data Index: 18921 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2050. Min Act: -0.0000

Data Index: 983754 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1027435 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2103. Min Act: -0.0000

Data Index: 236028 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2014. Min Act: -0.0000

Data Index: 480843 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1986. Min Act: -0.0000

Data Index: 65734 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1838. Min Act: -0.0000

Data Index: 321888 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2058. Min Act: -0.0000

Data Index: 674227 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1285250 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1263588 (C4 (Web Text))

Max Activating Token Index: 651