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

Dataset: The Pile

Neuron 3825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1086469 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1727728 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1423601 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7881. Min Act: -0.0000

Data Index: 981522 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6491. Min Act: -0.0000

Data Index: 115668 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8486. Min Act: -0.0000

Data Index: 462641 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7938. Min Act: -0.0000

Data Index: 334789 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7968. Min Act: -0.0000

Data Index: 405425 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8330. Min Act: -0.0000

Data Index: 519214 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6816. Min Act: -0.0000

Data Index: 32461 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7977. Min Act: -0.0000

Data Index: 632566 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.5646. Min Act: -0.0000

Data Index: 173425 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1927248 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1501279 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7717. Min Act: -0.0000

Data Index: 861698 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1350564 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1173801 (The Pile)

Max Activating Token Index: 749

Text #17

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7225. Min Act: -0.0000

Data Index: 64015 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7200. Min Act: -0.0000

Data Index: 5034 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1055991 (The Pile)

Max Activating Token Index: 810