Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3979 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1837. Min Act: -0.0002

Data Index: 1120702 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1799. Min Act: -0.0002

Data Index: 624664 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1773. Min Act: -0.0003

Data Index: 413690 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1753. Min Act: -0.0002

Data Index: 289377 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1726. Min Act: -0.0003

Data Index: 1024727 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1720. Min Act: -0.0002

Data Index: 372513 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1723. Min Act: -0.0003

Data Index: 951904 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1703. Min Act: -0.0002

Data Index: 1318914 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1701. Min Act: -0.0002

Data Index: 1253486 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1661. Min Act: -0.0002

Data Index: 271966 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1705. Min Act: -0.0002

Data Index: 15713 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1690. Min Act: -0.0003

Data Index: 436463 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1653. Min Act: -0.0002

Data Index: 859274 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1628. Min Act: -0.0002

Data Index: 798030 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1661. Min Act: -0.0002

Data Index: 1253911 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1621. Min Act: -0.0002

Data Index: 285335 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1649. Min Act: -0.0002

Data Index: 475343 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1657. Min Act: -0.0002

Data Index: 945634 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1610. Min Act: -0.0002

Data Index: 1080511 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.1837. Min Range: -0.1837

Max Act: 0.1642. Min Act: -0.0003

Data Index: 753295 (C4 (Web Text))

Max Activating Token Index: 175