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

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

Neuron 334 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: 0.2006. Min Range: -0.2006

Max Act: 0.1985. Min Act: -0.0000

Data Index: 908354 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.2006. Min Act: -0.0000

Data Index: 498023 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1771. Min Act: -0.0000

Data Index: 872068 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1059576 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1693. Min Act: -0.0000

Data Index: 740557 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1785. Min Act: -0.0000

Data Index: 207398 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1190614 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1719. Min Act: -0.0000

Data Index: 325952 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1647. Min Act: -0.0000

Data Index: 262546 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1069412 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1643. Min Act: -0.0000

Data Index: 515412 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1593. Min Act: -0.0000

Data Index: 772099 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1505. Min Act: -0.0000

Data Index: 824620 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1600. Min Act: -0.0000

Data Index: 785297 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1435. Min Act: -0.0000

Data Index: 399087 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1588. Min Act: -0.0000

Data Index: 945768 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1474. Min Act: -0.0000

Data Index: 967566 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1459. Min Act: -0.0000

Data Index: 544561 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1562. Min Act: -0.0000

Data Index: 400315 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.2006. Min Range: -0.2006

Max Act: 0.1511. Min Act: -0.0000

Data Index: 439989 (C4 (Web Text))

Max Activating Token Index: 163