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

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

Neuron 1557 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2381. Min Act: -0.0001

Data Index: 530683 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2046. Min Act: -0.0001

Data Index: 408386 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2155. Min Act: -0.0001

Data Index: 378561 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2037. Min Act: -0.0001

Data Index: 549285 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1967. Min Act: -0.0000

Data Index: 15257 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1999. Min Act: -0.0001

Data Index: 897031 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2136. Min Act: -0.0001

Data Index: 705382 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2095. Min Act: -0.0000

Data Index: 948679 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1064014 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2277. Min Act: -0.0000

Data Index: 404559 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2056. Min Act: -0.0001

Data Index: 251479 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.2017. Min Act: -0.0000

Data Index: 78259 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1861. Min Act: -0.0000

Data Index: 369932 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1884. Min Act: -0.0000

Data Index: 908358 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1126396 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1908. Min Act: -0.0000

Data Index: 122792 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1097733 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1750. Min Act: -0.0000

Data Index: 160765 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1924. Min Act: -0.0000

Data Index: 912953 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.2381. Min Range: -0.2381

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1016329 (C4 (Web Text))

Max Activating Token Index: 479