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

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

Neuron 4846 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1482761 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1611691 (Python Code)

Max Activating Token Index: 763

Text #2

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1547907 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1481760 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1600511 (Python Code)

Max Activating Token Index: 702

Text #5

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8917. Min Act: -0.0000

Data Index: 889939 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1507188 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.9012. Min Act: -0.0000

Data Index: 709902 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1033230 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1371243 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1621982 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1624990 (Python Code)

Max Activating Token Index: 563

Text #12

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1441361 (Python Code)

Max Activating Token Index: 366

Text #13

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1500688 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1603435 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1625964 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1418122 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1387809 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8345. Min Act: -0.0000

Data Index: 397639 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.9517. Min Range: -0.9517

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1471320 (Python Code)

Max Activating Token Index: 189