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

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

Neuron 2077 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: 0.2110. Min Range: -0.2110

Max Act: 0.2110. Min Act: -0.0001

Data Index: 558746 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1971. Min Act: -0.0001

Data Index: 795832 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1887. Min Act: -0.0001

Data Index: 947918 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1820. Min Act: -0.0001

Data Index: 563883 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1087019 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1836. Min Act: -0.0001

Data Index: 52991 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1724. Min Act: -0.0001

Data Index: 70419 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.2010. Min Act: -0.0001

Data Index: 496279 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1202200 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1838. Min Act: -0.0001

Data Index: 12595 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1712. Min Act: -0.0001

Data Index: 401773 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1724. Min Act: -0.0001

Data Index: 479092 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1507. Min Act: -0.0001

Data Index: 934749 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1641. Min Act: -0.0001

Data Index: 142002 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1658. Min Act: -0.0001

Data Index: 491147 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1530. Min Act: -0.0001

Data Index: 853400 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1502. Min Act: -0.0001

Data Index: 927179 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1426. Min Act: -0.0001

Data Index: 838956 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1089681 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1546. Min Act: -0.0001

Data Index: 584328 (C4 (Web Text))

Max Activating Token Index: 785