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

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

Neuron 700 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.2106. Min Act: -0.0000

Data Index: 951953 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.2151. Min Act: -0.0000

Data Index: 43788 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.2116. Min Act: -0.0000

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1820. Min Act: -0.0000

Data Index: 224986 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1121670 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1819. Min Act: -0.0001

Data Index: 695988 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1716. Min Act: -0.0001

Data Index: 161658 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.2000. Min Act: -0.0000

Data Index: 309603 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1700. Min Act: -0.0000

Data Index: 273265 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1709. Min Act: -0.0000

Data Index: 453840 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1753. Min Act: -0.0001

Data Index: 11185 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1570. Min Act: -0.0000

Data Index: 231645 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1602. Min Act: -0.0000

Data Index: 444825 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1724. Min Act: -0.0000

Data Index: 148432 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1684. Min Act: -0.0000

Data Index: 385671 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1548. Min Act: -0.0000

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1664. Min Act: -0.0001

Data Index: 166572 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1125953 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1529. Min Act: -0.0000

Data Index: 300475 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1613. Min Act: -0.0000

Data Index: 247957 (C4 (Web Text))

Max Activating Token Index: 892