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

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

Neuron 2268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2648. Min Act: -0.0000

Data Index: 483012 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2583. Min Act: -0.0000

Data Index: 387289 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2079. Min Act: -0.0000

Data Index: 821733 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2234. Min Act: -0.0000

Data Index: 397827 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1020305 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2175. Min Act: -0.0000

Data Index: 308626 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1056405 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2011. Min Act: -0.0000

Data Index: 812737 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2087. Min Act: -0.0000

Data Index: 892191 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1984. Min Act: -0.0000

Data Index: 804897 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1343490 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1977. Min Act: -0.0000

Data Index: 25379 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1891. Min Act: -0.0000

Data Index: 74236 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1933. Min Act: -0.0000

Data Index: 978614 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1985. Min Act: -0.0000

Data Index: 775577 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1879. Min Act: -0.0000

Data Index: 939539 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1917. Min Act: -0.0000

Data Index: 89309 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1862. Min Act: -0.0000

Data Index: 10551 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1867. Min Act: -0.0001

Data Index: 565531 (C4 (Web Text))

Max Activating Token Index: 331