Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1829 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.3600. Min Act: -0.0001

Data Index: 530338 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2828. Min Act: -0.0001

Data Index: 1260569 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2420. Min Act: -0.0001

Data Index: 109309 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2331. Min Act: -0.0001

Data Index: 208679 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2212. Min Act: -0.0001

Data Index: 1301113 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2326. Min Act: -0.0001

Data Index: 351197 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1936. Min Act: -0.0001

Data Index: 158127 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1085173 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1341668 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1821. Min Act: -0.0001

Data Index: 81150 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1772. Min Act: -0.0001

Data Index: 434053 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1751. Min Act: -0.0001

Data Index: 550657 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1677. Min Act: -0.0001

Data Index: 436160 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1653. Min Act: -0.0001

Data Index: 436462 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1233483 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1523. Min Act: -0.0001

Data Index: 129426 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1628. Min Act: -0.0001

Data Index: 848412 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1349822 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1443. Min Act: -0.0001

Data Index: 729676 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.1418. Min Act: -0.0001

Data Index: 868697 (C4 (Web Text))

Max Activating Token Index: 528