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

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

Neuron 3427 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 208007 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0853. Min Act: -0.0000

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0753. Min Act: -0.0000

Data Index: 993627 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0710. Min Act: -0.0000

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0733. Min Act: -0.0000

Data Index: 29461 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1048637 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0686. Min Act: -0.0000

Data Index: 713065 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0673. Min Act: -0.0000

Data Index: 496319 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0667. Min Act: -0.0000

Data Index: 339363 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0636. Min Act: -0.0000

Data Index: 761849 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0683. Min Act: -0.0000

Data Index: 897982 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1186865 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1160471 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0651. Min Act: -0.0000

Data Index: 991704 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0648. Min Act: -0.0000

Data Index: 334900 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0649. Min Act: -0.0000

Data Index: 100696 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0636. Min Act: -0.0000

Data Index: 278415 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0634. Min Act: -0.0000

Data Index: 279792 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0613. Min Act: -0.0000

Data Index: 887700 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1276287 (C4 (Web Text))

Max Activating Token Index: 324