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

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

Neuron 3171 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0001

Data Index: 406305 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0493. Min Act: -0.0001

Data Index: 644005 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1155701 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0392. Min Act: -0.0001

Data Index: 830094 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0404. Min Act: -0.0001

Data Index: 235192 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0366. Min Act: -0.0001

Data Index: 507074 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0412. Min Act: -0.0001

Data Index: 755578 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0390. Min Act: -0.0001

Data Index: 367212 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0352. Min Act: -0.0001

Data Index: 259170 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0382. Min Act: -0.0001

Data Index: 252315 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0342. Min Act: -0.0001

Data Index: 148659 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1148701 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0297. Min Act: -0.0001

Data Index: 640049 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0361. Min Act: -0.0001

Data Index: 360708 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0284. Min Act: -0.0001

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1586697 (Python Code)

Max Activating Token Index: 670

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0312. Min Act: -0.0001

Data Index: 934505 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1411276 (Python Code)

Max Activating Token Index: 111

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0341. Min Act: -0.0001

Data Index: 1190870 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1409952 (Python Code)

Max Activating Token Index: 224