Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0005

Data Index: 768559 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0427. Min Act: -0.0005

Data Index: 934831 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0396. Min Act: -0.0005

Data Index: 235926 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0393. Min Act: -0.0005

Data Index: 973813 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0381. Min Act: -0.0005

Data Index: 268330 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1015453 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0365. Min Act: -0.0005

Data Index: 908593 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0378. Min Act: -0.0005

Data Index: 1135125 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1166388 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0392. Min Act: -0.0005

Data Index: 533489 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0380. Min Act: -0.0005

Data Index: 467195 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1337439 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0357. Min Act: -0.0005

Data Index: 1311276 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0346. Min Act: -0.0005

Data Index: 335811 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0351. Min Act: -0.0005

Data Index: 895506 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0350. Min Act: -0.0005

Data Index: 396478 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0351. Min Act: -0.0005

Data Index: 659173 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0334. Min Act: -0.0005

Data Index: 1084221 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0334. Min Act: -0.0005

Data Index: 966605 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0357. Min Act: -0.0005

Data Index: 675157 (C4 (Web Text))

Max Activating Token Index: 29