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

Dataset: The Pile

Neuron 1082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.9964. Min Act: -0.0000

Data Index: 59691 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.7855. Min Act: -0.0000

Data Index: 480346 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.9996. Min Act: -0.0000

Data Index: 1344204 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.8245. Min Act: -0.0000

Data Index: 1480857 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.5662. Min Act: -0.0000

Data Index: 1388112 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.3387. Min Act: -0.0000

Data Index: 1112375 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.1871. Min Act: -0.0000

Data Index: 1785104 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.8918. Min Act: -0.0000

Data Index: 1387551 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.1667. Min Act: -0.0000

Data Index: 1257846 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.9826. Min Act: -0.0000

Data Index: 1115250 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.9693. Min Act: -0.0000

Data Index: 847851 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.0627. Min Act: -0.0000

Data Index: 1252454 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.0277. Min Act: -0.0000

Data Index: 426630 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.8966. Min Act: -0.0000

Data Index: 994513 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.0066. Min Act: -0.0000

Data Index: 240812 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.8769. Min Act: -0.0000

Data Index: 764986 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.8847. Min Act: -0.0000

Data Index: 1739483 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.7128. Min Act: -0.0000

Data Index: 1083931 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1594433 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 3.9996. Min Range: -3.9996

Max Act: 2.8464. Min Act: -0.0000

Data Index: 1346542 (The Pile)

Max Activating Token Index: 269