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

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

Neuron 498 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: 0.2073. Min Range: -0.2073

Max Act: 0.2073. Min Act: -0.0001

Data Index: 228475 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1765. Min Act: -0.0001

Data Index: 206349 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1338642 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1876. Min Act: -0.0001

Data Index: 231174 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1745. Min Act: -0.0001

Data Index: 484536 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1040232 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1950. Min Act: -0.0001

Data Index: 1288404 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1771. Min Act: -0.0001

Data Index: 542148 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1790. Min Act: -0.0001

Data Index: 336067 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1742. Min Act: -0.0001

Data Index: 320418 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1740. Min Act: -0.0001

Data Index: 712504 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1675. Min Act: -0.0001

Data Index: 82784 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1348245 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1720. Min Act: -0.0001

Data Index: 378738 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1839. Min Act: -0.0001

Data Index: 1067345 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1694. Min Act: -0.0001

Data Index: 990255 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1610. Min Act: -0.0001

Data Index: 420393 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1225976 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1139243 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1637. Min Act: -0.0001

Data Index: 323969 (C4 (Web Text))

Max Activating Token Index: 294