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

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

Neuron 4373 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: 0.7821. Min Range: -0.7821

Max Act: 0.7821. Min Act: 0.0000

Data Index: 519455 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1010922 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1193095 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6203. Min Act: -0.0000

Data Index: 865580 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6328. Min Act: -0.0000

Data Index: 755393 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6383. Min Act: -0.0000

Data Index: 333595 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6217. Min Act: -0.0000

Data Index: 371931 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6165. Min Act: -0.0000

Data Index: 813780 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1149373 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5940. Min Act: -0.0000

Data Index: 558504 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5779. Min Act: -0.0000

Data Index: 392178 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5722. Min Act: -0.0000

Data Index: 540204 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1120138 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5611. Min Act: -0.0000

Data Index: 270730 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1104859 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5508. Min Act: -0.0000

Data Index: 255599 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6014. Min Act: -0.0000

Data Index: 129226 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5613. Min Act: -0.0000

Data Index: 560874 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5778. Min Act: -0.0000

Data Index: 242038 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5558. Min Act: -0.0000

Data Index: 712750 (C4 (Web Text))

Max Activating Token Index: 416