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

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

Neuron 2118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1896. Min Act: -0.0002

Data Index: 1355050 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1877. Min Act: -0.0002

Data Index: 263197 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1616. Min Act: -0.0002

Data Index: 19323 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1695. Min Act: -0.0002

Data Index: 1087254 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1635. Min Act: -0.0002

Data Index: 164053 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1816. Min Act: -0.0002

Data Index: 1121178 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1550. Min Act: -0.0002

Data Index: 1235549 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1717. Min Act: -0.0002

Data Index: 932791 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1820. Min Act: -0.0002

Data Index: 490756 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1590. Min Act: -0.0002

Data Index: 315883 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1575. Min Act: -0.0002

Data Index: 538062 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1469. Min Act: -0.0002

Data Index: 43863 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1513. Min Act: -0.0002

Data Index: 869694 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1525. Min Act: -0.0002

Data Index: 899806 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1543. Min Act: -0.0002

Data Index: 269 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1521. Min Act: -0.0002

Data Index: 1058233 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1554. Min Act: -0.0002

Data Index: 745213 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1528. Min Act: -0.0002

Data Index: 911585 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1528. Min Act: -0.0002

Data Index: 867527 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1369. Min Act: -0.0002

Data Index: 193968 (C4 (Web Text))

Max Activating Token Index: 284