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

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

Neuron 192 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: 0.9903. Min Range: -0.9903

Max Act: 0.9203. Min Act: -0.0000

Data Index: 193650 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1330776 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1034280 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.8841. Min Act: -0.0000

Data Index: 185942 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.7821. Min Act: -0.0000

Data Index: 504392 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.8962. Min Act: -0.0000

Data Index: 612488 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.7856. Min Act: -0.0000

Data Index: 233869 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.8399. Min Act: -0.0000

Data Index: 192998 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.7751. Min Act: -0.0000

Data Index: 2253 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1231814 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.8174. Min Act: -0.0000

Data Index: 933253 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.8123. Min Act: -0.0000

Data Index: 66513 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.7249. Min Act: -0.0000

Data Index: 226162 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.8017. Min Act: -0.0000

Data Index: 174921 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1151135 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.6563. Min Act: -0.0000

Data Index: 662460 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.7171. Min Act: -0.0000

Data Index: 851196 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.6938. Min Act: -0.0000

Data Index: 811733 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.6294. Min Act: -0.0000

Data Index: 851660 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.9903. Min Range: -0.9903

Max Act: 0.6439. Min Act: -0.0000

Data Index: 277008 (C4 (Web Text))

Max Activating Token Index: 973