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

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

Neuron 1395 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.6854. Min Act: -0.0000

Data Index: 1506540 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5157. Min Act: -0.0001

Data Index: 1469306 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3538. Min Act: -0.0000

Data Index: 1642351 (Python Code)

Max Activating Token Index: 763

Text #3

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.4822. Min Act: -0.0000

Data Index: 252879 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.5521. Min Act: -0.0001

Data Index: 1616373 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1590306 (Python Code)

Max Activating Token Index: 157

Text #6

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.4278. Min Act: -0.0001

Data Index: 1634757 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3405. Min Act: -0.0001

Data Index: 1333779 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1631885 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3253. Min Act: -0.0000

Data Index: 849411 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3627. Min Act: -0.0001

Data Index: 1655463 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1307777 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3400. Min Act: -0.0001

Data Index: 1363636 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3269. Min Act: -0.0001

Data Index: 1492173 (Python Code)

Max Activating Token Index: 473

Text #14

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2539. Min Act: -0.0001

Data Index: 1482993 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3644. Min Act: -0.0001

Data Index: 1411065 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3647. Min Act: -0.0000

Data Index: 1394497 (Python Code)

Max Activating Token Index: 289

Text #17

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.2762. Min Act: -0.0000

Data Index: 412469 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.3514. Min Act: -0.0000

Data Index: 45794 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 1.6854. Min Range: -1.6854

Max Act: 1.1965. Min Act: -0.0001

Data Index: 1446430 (Python Code)

Max Activating Token Index: 257