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

Dataset: The Pile

Neuron 3629 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: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: 0.0000

Data Index: 1095613 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0797. Min Act: -0.0000

Data Index: 838666 (The Pile)

Max Activating Token Index: 322

Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1679753 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0819. Min Act: -0.0000

Data Index: 776053 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1857079 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1052871 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1487710 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0775. Min Act: 0.0000

Data Index: 1326209 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1715846 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1580706 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1895673 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1031699 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0767. Min Act: 0.0000

Data Index: 828131 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0767. Min Act: -0.0000

Data Index: 251430 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1531618 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0764. Min Act: -0.0000

Data Index: 12588 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0759. Min Act: 0.0000

Data Index: 698554 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0760. Min Act: 0.0001

Data Index: 929567 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0760. Min Act: -0.0000

Data Index: 451853 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1589970 (The Pile)

Max Activating Token Index: 6