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

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

Neuron 3009 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1264953 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.2027. Min Act: -0.0001

Data Index: 915369 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.2034. Min Act: -0.0001

Data Index: 882688 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.2022. Min Act: -0.0001

Data Index: 657016 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1925. Min Act: -0.0001

Data Index: 309951 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1917. Min Act: -0.0001

Data Index: 431622 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1193693 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1745. Min Act: -0.0001

Data Index: 724074 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1869. Min Act: -0.0001

Data Index: 694307 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1690. Min Act: -0.0001

Data Index: 964751 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1661. Min Act: -0.0001

Data Index: 1298505 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1682. Min Act: -0.0001

Data Index: 30176 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1686. Min Act: -0.0001

Data Index: 467888 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1667. Min Act: -0.0001

Data Index: 541300 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1224564 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1604. Min Act: -0.0001

Data Index: 196945 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1196507 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1645. Min Act: -0.0001

Data Index: 556793 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1713. Min Act: -0.0001

Data Index: 10763 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.2111. Min Range: -0.2111

Max Act: 0.1601. Min Act: -0.0001

Data Index: 164688 (C4 (Web Text))

Max Activating Token Index: 168