Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1833 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2343. Min Act: -0.0003

Data Index: 1601466 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2358. Min Act: -0.0003

Data Index: 301806 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.2014. Min Act: -0.0003

Data Index: 1503426 (Python Code)

Max Activating Token Index: 311

Text #3

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1951. Min Act: -0.0003

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1951. Min Act: -0.0003

Data Index: 670743 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1963. Min Act: -0.0003

Data Index: 1534012 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1891. Min Act: -0.0003

Data Index: 1644596 (Python Code)

Max Activating Token Index: 587

Text #7

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1845. Min Act: -0.0003

Data Index: 1437806 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1768. Min Act: -0.0003

Data Index: 1408944 (Python Code)

Max Activating Token Index: 422

Text #9

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1969. Min Act: -0.0003

Data Index: 660445 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1808. Min Act: -0.0003

Data Index: 1606549 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1928. Min Act: -0.0003

Data Index: 183264 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1935. Min Act: -0.0003

Data Index: 1470732 (Python Code)

Max Activating Token Index: 689

Text #13

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1872. Min Act: -0.0003

Data Index: 700460 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1803. Min Act: -0.0003

Data Index: 953066 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1829. Min Act: -0.0003

Data Index: 1556377 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1832. Min Act: -0.0003

Data Index: 515522 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1845. Min Act: -0.0003

Data Index: 1104595 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1845. Min Act: -0.0003

Data Index: 18062 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.2358. Min Range: -0.2358

Max Act: 0.1767. Min Act: -0.0003

Data Index: 1587520 (Python Code)

Max Activating Token Index: 683