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

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

Neuron 3005 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: 0.2341. Min Range: -0.2341

Max Act: 0.2341. Min Act: -0.0000

Data Index: 946426 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.2051. Min Act: -0.0000

Data Index: 913771 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1013326 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1768. Min Act: -0.0000

Data Index: 996211 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1811. Min Act: -0.0000

Data Index: 320847 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1815. Min Act: -0.0000

Data Index: 261943 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1860. Min Act: -0.0000

Data Index: 910573 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1796. Min Act: -0.0000

Data Index: 432950 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1782. Min Act: -0.0000

Data Index: 114617 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1790. Min Act: -0.0000

Data Index: 110408 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1776. Min Act: -0.0000

Data Index: 932824 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1856. Min Act: -0.0000

Data Index: 611784 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1764. Min Act: -0.0000

Data Index: 702876 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1777. Min Act: -0.0000

Data Index: 113520 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1218330 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1784. Min Act: -0.0000

Data Index: 857019 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1736. Min Act: -0.0000

Data Index: 157742 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1728. Min Act: -0.0000

Data Index: 98373 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1722. Min Act: -0.0000

Data Index: 395678 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.2341. Min Range: -0.2341

Max Act: 0.1718. Min Act: -0.0000

Data Index: 823392 (C4 (Web Text))

Max Activating Token Index: 99