Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1880 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: 0.0000

Data Index: 704571 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1102. Min Act: 0.0000

Data Index: 1562470 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1620425 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1045768 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0963. Min Act: -0.0000

Data Index: 926722 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1240907 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1473524 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0877. Min Act: -0.0000

Data Index: 960995 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0829. Min Act: -0.0000

Data Index: 551011 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1375838 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0824. Min Act: -0.0000

Data Index: 48869 (The Pile)

Max Activating Token Index: 129

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1644271 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0832. Min Act: -0.0000

Data Index: 946524 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0806. Min Act: -0.0000

Data Index: 128256 (The Pile)

Max Activating Token Index: 568

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0831. Min Act: -0.0000

Data Index: 260962 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0763. Min Act: -0.0000

Data Index: 959011 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1461231 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0725. Min Act: -0.0000

Data Index: 965081 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0767. Min Act: -0.0000

Data Index: 420013 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.0761. Min Act: -0.0000

Data Index: 82290 (The Pile)

Max Activating Token Index: 522