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

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

Neuron 1605 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1292. Min Act: -0.0000

Data Index: 802996 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1068. Min Act: -0.0000

Data Index: 895678 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1402456 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1038650 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0830. Min Act: -0.0000

Data Index: 696804 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0756. Min Act: -0.0000

Data Index: 66598 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1525089 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0767. Min Act: -0.0000

Data Index: 658578 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1541263 (Python Code)

Max Activating Token Index: 987

Text #9

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0816. Min Act: -0.0000

Data Index: 146744 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0776. Min Act: -0.0000

Data Index: 518357 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0749. Min Act: -0.0000

Data Index: 347447 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0766. Min Act: -0.0000

Data Index: 884227 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1573082 (Python Code)

Max Activating Token Index: 85

Text #14

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0669. Min Act: -0.0000

Data Index: 23792 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0786. Min Act: -0.0000

Data Index: 673059 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0667. Min Act: -0.0000

Data Index: 218413 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0742. Min Act: -0.0000

Data Index: 263725 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1084550 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0683. Min Act: -0.0000

Data Index: 62904 (C4 (Web Text))

Max Activating Token Index: 520