Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2039 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1890. Min Act: -0.0001

Data Index: 681030 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0001

Data Index: 478214 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1122667 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1761. Min Act: -0.0001

Data Index: 303523 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1806. Min Act: -0.0001

Data Index: 98132 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1160926 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1728. Min Act: -0.0001

Data Index: 417795 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1764. Min Act: -0.0001

Data Index: 694208 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1078143 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1767. Min Act: -0.0001

Data Index: 685316 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1634. Min Act: -0.0001

Data Index: 692676 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1731. Min Act: -0.0001

Data Index: 946275 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1787. Min Act: -0.0001

Data Index: 319830 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1711. Min Act: -0.0001

Data Index: 1194902 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1614. Min Act: -0.0001

Data Index: 147034 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1606. Min Act: -0.0001

Data Index: 844909 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1155522 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1636. Min Act: -0.0001

Data Index: 198598 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1633. Min Act: -0.0001

Data Index: 737062 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1681. Min Act: -0.0001

Data Index: 180914 (C4 (Web Text))

Max Activating Token Index: 645