Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 519 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2697. Min Act: -0.0003

Data Index: 1637102 (Python Code)

Max Activating Token Index: 875

Text #1

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2277. Min Act: -0.0003

Data Index: 257346 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2223. Min Act: -0.0003

Data Index: 1540416 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2001. Min Act: -0.0003

Data Index: 1530349 (Python Code)

Max Activating Token Index: 210

Text #4

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2014. Min Act: -0.0003

Data Index: 1517642 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1927. Min Act: -0.0003

Data Index: 741747 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1925. Min Act: -0.0003

Data Index: 1580316 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1894. Min Act: -0.0003

Data Index: 1474497 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1844. Min Act: -0.0003

Data Index: 1398574 (Python Code)

Max Activating Token Index: 439

Text #9

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1828. Min Act: -0.0003

Data Index: 1415336 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1734. Min Act: -0.0003

Data Index: 1579495 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1767. Min Act: -0.0003

Data Index: 1614030 (Python Code)

Max Activating Token Index: 796

Text #12

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1703. Min Act: -0.0003

Data Index: 1394376 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1713. Min Act: -0.0003

Data Index: 1440578 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1719. Min Act: -0.0003

Data Index: 1338581 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1711. Min Act: -0.0003

Data Index: 1654865 (Python Code)

Max Activating Token Index: 971

Text #16

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1713. Min Act: -0.0003

Data Index: 923169 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1724. Min Act: -0.0003

Data Index: 1422838 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1685. Min Act: -0.0003

Data Index: 336148 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1663. Min Act: -0.0003

Data Index: 1399902 (Python Code)

Max Activating Token Index: 757