Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4371 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0558. Min Act: -0.0003

Data Index: 715788 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1248982 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0518. Min Act: -0.0003

Data Index: 218660 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1640982 (Python Code)

Max Activating Token Index: 197

Text #4

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0456. Min Act: -0.0003

Data Index: 46755 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1394065 (Python Code)

Max Activating Token Index: 753

Text #6

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0421. Min Act: -0.0003

Data Index: 78919 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0419. Min Act: -0.0003

Data Index: 687849 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0419. Min Act: -0.0003

Data Index: 829465 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0402. Min Act: -0.0003

Data Index: 469616 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1483479 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1012741 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0399. Min Act: -0.0003

Data Index: 312218 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0390. Min Act: -0.0003

Data Index: 905582 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0388. Min Act: -0.0003

Data Index: 648112 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0390. Min Act: -0.0003

Data Index: 8978 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0392. Min Act: -0.0003

Data Index: 442795 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0377. Min Act: -0.0003

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1507333 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 0.0558. Min Range: -0.0558

Max Act: 0.0375. Min Act: -0.0003

Data Index: 939488 (C4 (Web Text))

Max Activating Token Index: 768