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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2169 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1170969 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0852. Min Act: -0.0000

Data Index: 831788 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0837. Min Act: -0.0000

Data Index: 710509 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0918. Min Act: -0.0000

Data Index: 249156 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0831. Min Act: -0.0000

Data Index: 860116 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1241165 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0799. Min Act: -0.0000

Data Index: 967701 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0790. Min Act: -0.0000

Data Index: 332792 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1247476 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0730. Min Act: -0.0000

Data Index: 192381 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0737. Min Act: -0.0000

Data Index: 12766 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0701. Min Act: -0.0000

Data Index: 235840 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1502352 (Python Code)

Max Activating Token Index: 863

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0614. Min Act: -0.0000

Data Index: 328618 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0734. Min Act: -0.0000

Data Index: 368751 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1403330 (Python Code)

Max Activating Token Index: 168

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1036207 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1501130 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0651. Min Act: -0.0000

Data Index: 157761 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0733. Min Act: -0.0000

Data Index: 993667 (C4 (Web Text))

Max Activating Token Index: 591