Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1180 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.8783. Min Act: -0.0000

Data Index: 1038241 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.7835. Min Act: -0.0000

Data Index: 590498 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.6327. Min Act: -0.0000

Data Index: 1323765 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.4962. Min Act: -0.0000

Data Index: 994 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.6095. Min Act: -0.0000

Data Index: 900980 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.4799. Min Act: -0.0000

Data Index: 1249703 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.4222. Min Act: -0.0000

Data Index: 678163 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.3853. Min Act: -0.0000

Data Index: 1265908 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.5226. Min Act: -0.0000

Data Index: 508542 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.2864. Min Act: -0.0000

Data Index: 793692 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.1423. Min Act: -0.0000

Data Index: 222757 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.2102. Min Act: -0.0000

Data Index: 964408 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.1680. Min Act: -0.0000

Data Index: 1115805 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.1053. Min Act: -0.0000

Data Index: 401438 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.0688. Min Act: -0.0000

Data Index: 781317 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.1733. Min Act: -0.0000

Data Index: 1141213 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.0383. Min Act: -0.0000

Data Index: 700478 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 2.8783. Min Range: -2.8783

Max Act: 2.1480. Min Act: -0.0000

Data Index: 857873 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 2.8783. Min Range: -2.8783

Max Act: 1.9927. Min Act: -0.0000

Data Index: 1059049 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 2.8783. Min Range: -2.8783

Max Act: 1.9718. Min Act: -0.0000

Data Index: 212185 (C4 (Web Text))

Max Activating Token Index: 631