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

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

Neuron 477 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: 0.2051. Min Range: -0.2051

Max Act: 0.2051. Min Act: -0.0001

Data Index: 742528 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1884. Min Act: -0.0001

Data Index: 550657 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1778. Min Act: -0.0001

Data Index: 868697 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1827. Min Act: -0.0001

Data Index: 65080 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1872. Min Act: -0.0001

Data Index: 51791 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1739. Min Act: -0.0001

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1734. Min Act: -0.0001

Data Index: 878925 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1785. Min Act: -0.0000

Data Index: 114379 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1693. Min Act: -0.0001

Data Index: 1329717 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1624. Min Act: -0.0001

Data Index: 814177 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1691. Min Act: -0.0001

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1672. Min Act: -0.0000

Data Index: 1280082 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1716. Min Act: -0.0000

Data Index: 147448 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1649. Min Act: -0.0001

Data Index: 330923 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1025389 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1348875 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1633. Min Act: -0.0001

Data Index: 831236 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1677. Min Act: -0.0001

Data Index: 223652 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1551. Min Act: -0.0001

Data Index: 174725 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.2051. Min Range: -0.2051

Max Act: 0.1579. Min Act: -0.0001

Data Index: 784454 (C4 (Web Text))

Max Activating Token Index: 400