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

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

Neuron 1847 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: 0.0449. Min Range: -0.0449

Max Act: 0.0449. Min Act: -0.0006

Data Index: 670749 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0441. Min Act: -0.0006

Data Index: 541564 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0430. Min Act: -0.0006

Data Index: 354349 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0363. Min Act: -0.0006

Data Index: 163269 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1564264 (Python Code)

Max Activating Token Index: 197

Text #5

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0373. Min Act: -0.0006

Data Index: 507980 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1088427 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0395. Min Act: -0.0006

Data Index: 679551 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1645323 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0372. Min Act: -0.0006

Data Index: 395887 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0372. Min Act: -0.0006

Data Index: 694581 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1555793 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0375. Min Act: -0.0006

Data Index: 24346 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0379. Min Act: -0.0006

Data Index: 1445736 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0370. Min Act: -0.0006

Data Index: 1480909 (Python Code)

Max Activating Token Index: 784

Text #15

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0360. Min Act: -0.0006

Data Index: 867953 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0376. Min Act: -0.0006

Data Index: 459674 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0382. Min Act: -0.0006

Data Index: 200715 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0358. Min Act: -0.0006

Data Index: 996742 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0449. Min Range: -0.0449

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1288163 (C4 (Web Text))

Max Activating Token Index: 214