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

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

Neuron 4117 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2495. Min Act: -0.0000

Data Index: 934622 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2364. Min Act: -0.0000

Data Index: 162954 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2122. Min Act: -0.0000

Data Index: 693560 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1812. Min Act: -0.0000

Data Index: 301308 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1260313 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1208892 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1867. Min Act: -0.0000

Data Index: 23175 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1882. Min Act: -0.0000

Data Index: 807059 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1345100 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1812. Min Act: -0.0000

Data Index: 977086 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1042318 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1653. Min Act: -0.0000

Data Index: 613780 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1012698 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1665. Min Act: -0.0000

Data Index: 429967 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1487. Min Act: -0.0000

Data Index: 905360 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1290550 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1508. Min Act: -0.0000

Data Index: 295384 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1522. Min Act: -0.0000

Data Index: 321698 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1434. Min Act: -0.0000

Data Index: 763716 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1357216 (C4 (Web Text))

Max Activating Token Index: 382