Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 867 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1485570 (Python Code)

Max Activating Token Index: 470

Text #1

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2484. Min Act: -0.0000

Data Index: 989293 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2388. Min Act: -0.0000

Data Index: 404788 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2392. Min Act: -0.0000

Data Index: 954581 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2409. Min Act: -0.0000

Data Index: 823918 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1336434 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2501. Min Act: -0.0000

Data Index: 641224 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2268. Min Act: -0.0000

Data Index: 219482 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2111. Min Act: -0.0000

Data Index: 70154 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1295574 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2199. Min Act: -0.0000

Data Index: 69779 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2139. Min Act: -0.0000

Data Index: 701771 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2182. Min Act: -0.0000

Data Index: 638248 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1509013 (Python Code)

Max Activating Token Index: 579

Text #14

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2005. Min Act: -0.0000

Data Index: 323559 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2215. Min Act: -0.0000

Data Index: 648075 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.2039. Min Act: -0.0000

Data Index: 11182 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1898. Min Act: -0.0000

Data Index: 188486 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1632004 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 0.2744. Min Range: -0.2744

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1559096 (Python Code)

Max Activating Token Index: 68