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

Dataset: The Pile

Neuron 3150 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: 0.2462. Min Range: -0.2462

Max Act: 0.2401. Min Act: -0.0000

Data Index: 229246 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2462. Min Act: -0.0000

Data Index: 459641 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2034. Min Act: -0.0000

Data Index: 785998 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1359324 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1858496 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2158. Min Act: -0.0000

Data Index: 728691 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2072. Min Act: -0.0000

Data Index: 164906 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2020. Min Act: -0.0000

Data Index: 161978 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1248909 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1985. Min Act: -0.0000

Data Index: 352045 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1970. Min Act: -0.0000

Data Index: 53803 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1707063 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1256412 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1997. Min Act: -0.0000

Data Index: 977432 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1952793 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1917. Min Act: -0.0000

Data Index: 383017 (The Pile)

Max Activating Token Index: 398

Text #16

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1157137 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1857. Min Act: -0.0000

Data Index: 155621 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1217065 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1723743 (The Pile)

Max Activating Token Index: 686