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

Dataset: The Pile

Neuron 3195 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: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1452811 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1838179 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1506687 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1297685 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1089. Min Act: -0.0000

Data Index: 693968 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1003945 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0973. Min Act: -0.0000

Data Index: 356668 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1588879 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1844186 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0964. Min Act: -0.0000

Data Index: 304250 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1795880 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0881. Min Act: -0.0000

Data Index: 44769 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1311812 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1719015 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0878. Min Act: -0.0000

Data Index: 906039 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0880. Min Act: -0.0000

Data Index: 229454 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1243486 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0784. Min Act: -0.0000

Data Index: 153706 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0837. Min Act: -0.0000

Data Index: 77917 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1314116 (The Pile)

Max Activating Token Index: 771