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

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

Neuron 2496 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.2065. Min Act: -0.0001

Data Index: 653933 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.2029. Min Act: -0.0001

Data Index: 213724 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1772. Min Act: -0.0001

Data Index: 365447 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1856. Min Act: -0.0001

Data Index: 225396 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1641. Min Act: -0.0001

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1729. Min Act: -0.0001

Data Index: 464804 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1216931 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1778. Min Act: -0.0001

Data Index: 436747 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1814. Min Act: -0.0001

Data Index: 516483 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1765. Min Act: -0.0001

Data Index: 982572 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1874. Min Act: -0.0001

Data Index: 245102 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1633. Min Act: -0.0001

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1612. Min Act: -0.0001

Data Index: 650779 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1278820 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1136872 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1154607 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1782. Min Act: -0.0001

Data Index: 924403 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1721. Min Act: -0.0001

Data Index: 190776 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1604. Min Act: -0.0001

Data Index: 423061 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.2065. Min Range: -0.2065

Max Act: 0.1625. Min Act: -0.0001

Data Index: 927438 (C4 (Web Text))

Max Activating Token Index: 371