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

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

Neuron 578 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2280. Min Act: -0.0001

Data Index: 494435 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2321. Min Act: -0.0001

Data Index: 705370 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1224623 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2201. Min Act: -0.0001

Data Index: 811058 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1918. Min Act: -0.0001

Data Index: 782674 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1971. Min Act: -0.0001

Data Index: 842837 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1162391 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1813. Min Act: -0.0001

Data Index: 390452 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1194830 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1654. Min Act: -0.0001

Data Index: 5127 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1684. Min Act: -0.0001

Data Index: 345258 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1759. Min Act: -0.0001

Data Index: 884668 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1683. Min Act: -0.0001

Data Index: 871569 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1358804 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1615. Min Act: -0.0001

Data Index: 10740 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1660. Min Act: -0.0001

Data Index: 520265 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1678. Min Act: -0.0001

Data Index: 269120 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1251872 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1087836 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1418. Min Act: -0.0001

Data Index: 43543 (C4 (Web Text))

Max Activating Token Index: 1002