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

Dataset: The Pile

Neuron 4698 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: 0.2325. Min Range: -0.2325

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1197779 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1263891 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1572540 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1927. Min Act: -0.0000

Data Index: 215001 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1850811 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1102249 (The Pile)

Max Activating Token Index: 732

Text #6

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1810. Min Act: -0.0000

Data Index: 972140 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1629339 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1849174 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1035472 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1971296 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1236307 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1663. Min Act: -0.0000

Data Index: 314629 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1404513 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1712564 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1733. Min Act: -0.0000

Data Index: 160451 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1574. Min Act: -0.0000

Data Index: 212554 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1185077 (The Pile)

Max Activating Token Index: 445

Text #18

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1482. Min Act: -0.0000

Data Index: 854670 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1590. Min Act: -0.0000

Data Index: 459987 (The Pile)

Max Activating Token Index: 15