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

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

Neuron 360 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1295802 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0473. Min Act: -0.0006

Data Index: 124668 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0453. Min Act: -0.0006

Data Index: 1320999 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0418. Min Act: -0.0006

Data Index: 27894 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0408. Min Act: -0.0006

Data Index: 1033106 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0387. Min Act: -0.0006

Data Index: 246301 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0416. Min Act: -0.0006

Data Index: 1075423 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0405. Min Act: -0.0006

Data Index: 249460 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0395. Min Act: -0.0006

Data Index: 768061 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0413. Min Act: -0.0006

Data Index: 1338949 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0411. Min Act: -0.0006

Data Index: 1137846 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0393. Min Act: -0.0006

Data Index: 208724 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1186348 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0402. Min Act: -0.0006

Data Index: 843076 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0395. Min Act: -0.0006

Data Index: 347226 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1218900 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0369. Min Act: -0.0006

Data Index: 529896 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0382. Min Act: -0.0006

Data Index: 845721 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0389. Min Act: -0.0006

Data Index: 478947 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0382. Min Act: -0.0006

Data Index: 611508 (C4 (Web Text))

Max Activating Token Index: 626