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

Dataset: The Pile

Neuron 3130 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: 0.0000

Data Index: 706488 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0606. Min Act: 0.0000

Data Index: 1988084 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0605. Min Act: 0.0000

Data Index: 1600934 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0604. Min Act: 0.0000

Data Index: 824962 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0600. Min Act: 0.0000

Data Index: 1720943 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0601. Min Act: 0.0000

Data Index: 1965745 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0599. Min Act: 0.0000

Data Index: 758780 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0594. Min Act: 0.0000

Data Index: 1336104 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0593. Min Act: 0.0000

Data Index: 1100992 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1582784 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0588. Min Act: 0.0000

Data Index: 1818336 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0588. Min Act: 0.0000

Data Index: 1781803 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0586. Min Act: 0.0000

Data Index: 338806 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0586. Min Act: 0.0000

Data Index: 1306060 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0585. Min Act: 0.0000

Data Index: 678432 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0584. Min Act: 0.0000

Data Index: 1229788 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0602. Min Act: 0.0000

Data Index: 6107 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0602. Min Act: -0.0000

Data Index: 489042 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0579. Min Act: 0.0000

Data Index: 174760 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0579. Min Act: 0.0000

Data Index: 1180288 (The Pile)

Max Activating Token Index: 1023