Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4471 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1136604 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1247. Min Act: -0.0002

Data Index: 700790 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1193. Min Act: -0.0002

Data Index: 289918 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1301632 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1096746 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1017. Min Act: -0.0002

Data Index: 851916 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1008. Min Act: -0.0002

Data Index: 163768 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0991. Min Act: -0.0002

Data Index: 123976 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1352305 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0901. Min Act: -0.0002

Data Index: 992601 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0919. Min Act: -0.0002

Data Index: 649888 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0908. Min Act: -0.0002

Data Index: 28451 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0867. Min Act: -0.0002

Data Index: 168588 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0895. Min Act: -0.0002

Data Index: 554070 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0798. Min Act: -0.0002

Data Index: 735676 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1278985 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0849. Min Act: -0.0002

Data Index: 954236 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1231658 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0841. Min Act: -0.0002

Data Index: 406883 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1034406 (C4 (Web Text))

Max Activating Token Index: 901