Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1315 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.3949. Min Act: -0.0001

Data Index: 248069 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1246095 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2610. Min Act: -0.0001

Data Index: 765301 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2392. Min Act: -0.0001

Data Index: 697986 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2349. Min Act: -0.0001

Data Index: 670128 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2421. Min Act: -0.0001

Data Index: 425769 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2370. Min Act: -0.0001

Data Index: 257107 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2238. Min Act: -0.0001

Data Index: 1386697 (Python Code)

Max Activating Token Index: 536

Text #8

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1026310 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1035713 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2102. Min Act: -0.0001

Data Index: 743428 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1094613 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.2116. Min Act: -0.0001

Data Index: 984617 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.1987. Min Act: -0.0001

Data Index: 23879 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1005303 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.1829. Min Act: -0.0001

Data Index: 1420337 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.1811. Min Act: -0.0001

Data Index: 12916 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1279240 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.1678. Min Act: -0.0001

Data Index: 760298 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.3949. Min Range: -0.3949

Max Act: 0.1735. Min Act: -0.0001

Data Index: 244824 (C4 (Web Text))

Max Activating Token Index: 462