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

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

Neuron 4684 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: 0.2458. Min Range: -0.2458

Max Act: 0.2458. Min Act: -0.0000

Data Index: 551163 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2339. Min Act: -0.0000

Data Index: 91358 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1068996 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1285086 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1331040 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1860. Min Act: -0.0000

Data Index: 233188 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1898. Min Act: -0.0000

Data Index: 519119 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1849. Min Act: -0.0000

Data Index: 174792 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1823. Min Act: -0.0000

Data Index: 62894 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1822. Min Act: -0.0000

Data Index: 610644 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1087682 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1836. Min Act: -0.0000

Data Index: 278560 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1710. Min Act: -0.0000

Data Index: 889476 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1231046 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1709. Min Act: -0.0000

Data Index: 994631 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1186058 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1064198 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1741. Min Act: -0.0000

Data Index: 464750 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1705. Min Act: -0.0000

Data Index: 370969 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.2458. Min Range: -0.2458

Max Act: 0.1605. Min Act: -0.0000

Data Index: 473642 (C4 (Web Text))

Max Activating Token Index: 957