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

Dataset: The Pile

Neuron 1547 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: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 481729 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1736948 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1786163 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 134517 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: 0.0000

Data Index: 967902 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1599042 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1594323 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 758724 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 610274 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0000

Data Index: 604623 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1741469 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 798260 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 743413 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1040555 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 546617 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1441573 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 334807 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1408639 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1682150 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1708659 (The Pile)

Max Activating Token Index: 1