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

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

Neuron 3041 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: 1.2306. Min Range: -1.2306

Max Act: 1.2306. Min Act: -0.0000

Data Index: 631918 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.1699. Min Act: -0.0000

Data Index: 645632 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.1652. Min Act: -0.0000

Data Index: 673301 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.1302. Min Act: -0.0000

Data Index: 881459 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.0583. Min Act: -0.0000

Data Index: 586331 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.0807. Min Act: -0.0000

Data Index: 434966 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.0823. Min Act: -0.0000

Data Index: 589799 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1344771 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 1.2306. Min Range: -1.2306

Max Act: 1.0009. Min Act: -0.0000

Data Index: 318567 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9338. Min Act: -0.0000

Data Index: 230542 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9733. Min Act: -0.0000

Data Index: 655357 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9848. Min Act: -0.0000

Data Index: 279163 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9448. Min Act: -0.0000

Data Index: 327688 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.8894. Min Act: -0.0000

Data Index: 664373 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9369. Min Act: -0.0000

Data Index: 94347 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1094650 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9727. Min Act: -0.0000

Data Index: 392957 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.8549. Min Act: -0.0000

Data Index: 912048 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.9057. Min Act: -0.0000

Data Index: 72544 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.2306. Min Range: -1.2306

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1012445 (C4 (Web Text))

Max Activating Token Index: 412