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

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

Neuron 1805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2308. Min Act: -0.0000

Data Index: 465802 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1129133 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1877. Min Act: -0.0000

Data Index: 370102 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1196142 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1787. Min Act: -0.0000

Data Index: 491374 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1916. Min Act: -0.0000

Data Index: 613772 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1348013 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1563. Min Act: -0.0000

Data Index: 583891 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1608. Min Act: -0.0000

Data Index: 724572 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1628. Min Act: -0.0000

Data Index: 62155 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1560. Min Act: -0.0000

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1573. Min Act: -0.0000

Data Index: 148766 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1666. Min Act: -0.0000

Data Index: 999801 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1509. Min Act: -0.0000

Data Index: 545142 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1603. Min Act: -0.0000

Data Index: 961165 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1552. Min Act: -0.0000

Data Index: 854236 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1285501 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1229544 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1515. Min Act: -0.0000

Data Index: 785386 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1234317 (C4 (Web Text))

Max Activating Token Index: 782