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

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

Neuron 100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.9805. Min Act: -0.0000

Data Index: 1468941 (Python Code)

Max Activating Token Index: 760

Text #1

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.9055. Min Act: -0.0000

Data Index: 1543801 (Python Code)

Max Activating Token Index: 509

Text #2

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1443408 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.8008. Min Act: -0.0000

Data Index: 1392415 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.7773. Min Act: -0.0000

Data Index: 1460662 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6790. Min Act: -0.0000

Data Index: 1515830 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.7188. Min Act: -0.0000

Data Index: 1532284 (Python Code)

Max Activating Token Index: 512

Text #7

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1433551 (Python Code)

Max Activating Token Index: 432

Text #8

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1499321 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6020. Min Act: -0.0000

Data Index: 1533744 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6960. Min Act: -0.0000

Data Index: 1498260 (Python Code)

Max Activating Token Index: 831

Text #11

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1495522 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1459170 (Python Code)

Max Activating Token Index: 184

Text #13

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6620. Min Act: -0.0000

Data Index: 1573883 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1402348 (Python Code)

Max Activating Token Index: 757

Text #15

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.9727. Min Act: -0.0000

Data Index: 1437301 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.5581. Min Act: -0.0000

Data Index: 1625651 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1509035 (Python Code)

Max Activating Token Index: 345

Text #18

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6397. Min Act: -0.0000

Data Index: 1592548 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 1.9805. Min Range: -1.9805

Max Act: 1.6317. Min Act: -0.0001

Data Index: 1440835 (Python Code)

Max Activating Token Index: 951