Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 420 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0000

Data Index: 229170 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1934. Min Act: -0.0000

Data Index: 449726 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1966. Min Act: -0.0000

Data Index: 693211 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1903. Min Act: -0.0000

Data Index: 150331 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1754. Min Act: -0.0000

Data Index: 663906 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1727. Min Act: -0.0001

Data Index: 424494 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1710. Min Act: -0.0001

Data Index: 794936 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1696. Min Act: -0.0000

Data Index: 887350 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1752. Min Act: -0.0000

Data Index: 599618 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1730. Min Act: -0.0000

Data Index: 80991 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1725. Min Act: -0.0000

Data Index: 742928 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1713. Min Act: -0.0000

Data Index: 741699 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1760. Min Act: -0.0000

Data Index: 341633 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1691. Min Act: -0.0000

Data Index: 219866 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1633. Min Act: -0.0000

Data Index: 964165 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1274884 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1675. Min Act: -0.0000

Data Index: 313781 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1153896 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1729. Min Act: -0.0000

Data Index: 745135 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1605. Min Act: -0.0000

Data Index: 670564 (C4 (Web Text))

Max Activating Token Index: 929