Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.2243. Min Range: -7.2243

Max Act: 7.2243. Min Act: -0.0000

Data Index: 1643799 (Python Code)

Max Activating Token Index: 702

Text #1

Max Range: 7.2243. Min Range: -7.2243

Max Act: 6.7242. Min Act: -0.0000

Data Index: 1413047 (Python Code)

Max Activating Token Index: 166

Text #2

Max Range: 7.2243. Min Range: -7.2243

Max Act: 6.8754. Min Act: -0.0000

Data Index: 1381853 (Python Code)

Max Activating Token Index: 434

Text #3

Max Range: 7.2243. Min Range: -7.2243

Max Act: 6.5743. Min Act: -0.0000

Data Index: 1541065 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 7.2243. Min Range: -7.2243

Max Act: 6.5316. Min Act: -0.0000

Data Index: 1374948 (Python Code)

Max Activating Token Index: 494

Text #5

Max Range: 7.2243. Min Range: -7.2243

Max Act: 6.4402. Min Act: -0.0000

Data Index: 1614465 (Python Code)

Max Activating Token Index: 618

Text #6

Max Range: 7.2243. Min Range: -7.2243

Max Act: 6.2095. Min Act: -0.0000

Data Index: 1555122 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.4905. Min Act: -0.0000

Data Index: 1652742 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.7917. Min Act: -0.0000

Data Index: 1553263 (Python Code)

Max Activating Token Index: 223

Text #9

Max Range: 7.2243. Min Range: -7.2243

Max Act: 6.0829. Min Act: -0.0000

Data Index: 1433467 (Python Code)

Max Activating Token Index: 407

Text #10

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.1602. Min Act: -0.0000

Data Index: 1568771 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.3614. Min Act: -0.0000

Data Index: 1627961 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.4910. Min Act: -0.0000

Data Index: 1632489 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.6419. Min Act: -0.0000

Data Index: 1429927 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.2246. Min Act: -0.0000

Data Index: 1396762 (Python Code)

Max Activating Token Index: 995

Text #15

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.5514. Min Act: -0.0000

Data Index: 1508727 (Python Code)

Max Activating Token Index: 418

Text #16

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.1892. Min Act: -0.0000

Data Index: 1485704 (Python Code)

Max Activating Token Index: 165

Text #17

Max Range: 7.2243. Min Range: -7.2243

Max Act: 4.8282. Min Act: -0.0000

Data Index: 1483938 (Python Code)

Max Activating Token Index: 174

Text #18

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.7418. Min Act: -0.0000

Data Index: 1371505 (Python Code)

Max Activating Token Index: 291

Text #19

Max Range: 7.2243. Min Range: -7.2243

Max Act: 5.1227. Min Act: -0.0000

Data Index: 1536776 (Python Code)

Max Activating Token Index: 902