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

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

Neuron 1537 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.8004. Min Act: -0.0000

Data Index: 1619587 (Python Code)

Max Activating Token Index: 973

Text #1

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.5552. Min Act: -0.0000

Data Index: 1606776 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.4697. Min Act: -0.0000

Data Index: 1448528 (Python Code)

Max Activating Token Index: 603

Text #3

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.4519. Min Act: -0.0000

Data Index: 1562287 (Python Code)

Max Activating Token Index: 212

Text #4

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.2853. Min Act: -0.0000

Data Index: 1590550 (Python Code)

Max Activating Token Index: 883

Text #5

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.3333. Min Act: -0.0000

Data Index: 1408568 (Python Code)

Max Activating Token Index: 587

Text #6

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.1266. Min Act: -0.0000

Data Index: 1480398 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.1157. Min Act: -0.0000

Data Index: 1431329 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.1024. Min Act: -0.0000

Data Index: 1567824 (Python Code)

Max Activating Token Index: 84

Text #9

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.0792. Min Act: -0.0000

Data Index: 1500458 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.0400. Min Act: -0.0000

Data Index: 1423610 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.0610. Min Act: -0.0000

Data Index: 1441677 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 3.8004. Min Range: -3.8004

Max Act: 2.8906. Min Act: -0.0000

Data Index: 1395806 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.0075. Min Act: -0.0000

Data Index: 1631178 (Python Code)

Max Activating Token Index: 680

Text #14

Max Range: 3.8004. Min Range: -3.8004

Max Act: 2.9785. Min Act: -0.0000

Data Index: 1627550 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 3.8004. Min Range: -3.8004

Max Act: 2.8376. Min Act: -0.0000

Data Index: 1440172 (Python Code)

Max Activating Token Index: 503

Text #16

Max Range: 3.8004. Min Range: -3.8004

Max Act: 2.9394. Min Act: -0.0000

Data Index: 1639012 (Python Code)

Max Activating Token Index: 411

Text #17

Max Range: 3.8004. Min Range: -3.8004

Max Act: 2.9409. Min Act: -0.0000

Data Index: 1508072 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 3.8004. Min Range: -3.8004

Max Act: 3.0443. Min Act: -0.0000

Data Index: 1467845 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 3.8004. Min Range: -3.8004

Max Act: 2.8871. Min Act: -0.0000

Data Index: 1655977 (Python Code)

Max Activating Token Index: 142