Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 773 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0622. Min Act: -0.0005

Data Index: 1623404 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0597. Min Act: -0.0005

Data Index: 1497523 (Python Code)

Max Activating Token Index: 549

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0639. Min Act: -0.0005

Data Index: 1555856 (Python Code)

Max Activating Token Index: 90

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0005

Data Index: 1593388 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0600. Min Act: -0.0005

Data Index: 1487341 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0639. Min Act: -0.0005

Data Index: 1577106 (Python Code)

Max Activating Token Index: 463

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0599. Min Act: -0.0005

Data Index: 1619702 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0608. Min Act: -0.0005

Data Index: 1620791 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0636. Min Act: -0.0005

Data Index: 1368495 (Python Code)

Max Activating Token Index: 416

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0595. Min Act: -0.0005

Data Index: 1401105 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0619. Min Act: -0.0005

Data Index: 1559479 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0633. Min Act: -0.0005

Data Index: 1580827 (Python Code)

Max Activating Token Index: 418

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0616. Min Act: -0.0005

Data Index: 1489731 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0634. Min Act: -0.0005

Data Index: 1625640 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0614. Min Act: -0.0004

Data Index: 1583522 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0642. Min Act: -0.0005

Data Index: 1595684 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0591. Min Act: -0.0005

Data Index: 1364185 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0627. Min Act: -0.0005

Data Index: 1535353 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0565. Min Act: -0.0005

Data Index: 1648710 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0639. Min Act: -0.0005

Data Index: 1454971 (Python Code)

Max Activating Token Index: 303