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

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

Neuron 2653 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1397453 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1630779 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1368961 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1454681 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1393790 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1589600 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1609815 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1542354 (Python Code)

Max Activating Token Index: 642

Text #8

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1646681 (Python Code)

Max Activating Token Index: 386

Text #9

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1561034 (Python Code)

Max Activating Token Index: 574

Text #10

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1582408 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1572788 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1518017 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1461233 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1420506 (Python Code)

Max Activating Token Index: 357

Text #15

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1484778 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1586270 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1428766 (Python Code)

Max Activating Token Index: 84

Text #18

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1365809 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1630508 (Python Code)

Max Activating Token Index: 498