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

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

Neuron 188 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1844. Min Act: -0.0002

Data Index: 972552 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1775. Min Act: -0.0002

Data Index: 385442 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1838. Min Act: -0.0002

Data Index: 1597426 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1676. Min Act: -0.0002

Data Index: 128585 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1840. Min Act: -0.0002

Data Index: 949253 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1703. Min Act: -0.0002

Data Index: 859588 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1786. Min Act: -0.0002

Data Index: 769871 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1809. Min Act: -0.0002

Data Index: 1193874 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1617. Min Act: -0.0002

Data Index: 546252 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1734. Min Act: -0.0002

Data Index: 1535516 (Python Code)

Max Activating Token Index: 896

Text #10

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1601. Min Act: -0.0002

Data Index: 1459263 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1660. Min Act: -0.0002

Data Index: 924441 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1596. Min Act: -0.0002

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1654. Min Act: -0.0002

Data Index: 1383800 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1653. Min Act: -0.0002

Data Index: 321008 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1626. Min Act: -0.0002

Data Index: 1547475 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1617. Min Act: -0.0002

Data Index: 1108951 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1501. Min Act: -0.0002

Data Index: 939526 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1516. Min Act: -0.0002

Data Index: 692812 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.1844. Min Range: -0.1844

Max Act: 0.1731. Min Act: -0.0002

Data Index: 427431 (C4 (Web Text))

Max Activating Token Index: 378