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

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

Neuron 4061 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0220. Min Act: -0.0001

Data Index: 1609690 (Python Code)

Max Activating Token Index: 836

Text #1

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0203. Min Act: -0.0001

Data Index: 1382629 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0739. Min Act: -0.0001

Data Index: 1366984 (Python Code)

Max Activating Token Index: 876

Text #3

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0223. Min Act: -0.0001

Data Index: 1599758 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0797. Min Act: -0.0001

Data Index: 1382579 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9819. Min Act: -0.0001

Data Index: 1570449 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0306. Min Act: -0.0001

Data Index: 1490355 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9457. Min Act: -0.0001

Data Index: 1406285 (Python Code)

Max Activating Token Index: 961

Text #8

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9457. Min Act: -0.0001

Data Index: 1653268 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9722. Min Act: -0.0001

Data Index: 1383125 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 1.0797. Min Range: -1.0797

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1609089 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9662. Min Act: -0.0001

Data Index: 1637973 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1648263 (Python Code)

Max Activating Token Index: 731

Text #13

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9866. Min Act: -0.0001

Data Index: 1448581 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9775. Min Act: -0.0001

Data Index: 1367298 (Python Code)

Max Activating Token Index: 486

Text #15

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9458. Min Act: -0.0001

Data Index: 1381680 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9446. Min Act: -0.0001

Data Index: 1409363 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9575. Min Act: -0.0001

Data Index: 1470593 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9750. Min Act: -0.0001

Data Index: 1521453 (Python Code)

Max Activating Token Index: 656

Text #19

Max Range: 1.0797. Min Range: -1.0797

Max Act: 0.9581. Min Act: -0.0001

Data Index: 1520849 (Python Code)

Max Activating Token Index: 744