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

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

Neuron 3382 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2958. Min Act: -0.0000

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2740. Min Act: -0.0000

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1039060 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2300. Min Act: -0.0000

Data Index: 349362 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1313849 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2170. Min Act: -0.0000

Data Index: 5004 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2008. Min Act: -0.0000

Data Index: 176710 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.2086. Min Act: -0.0000

Data Index: 744617 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1325349 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1996. Min Act: -0.0000

Data Index: 331953 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1983. Min Act: -0.0000

Data Index: 40536 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1983. Min Act: -0.0000

Data Index: 833662 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1979. Min Act: -0.0000

Data Index: 417188 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1883. Min Act: -0.0000

Data Index: 708713 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1965. Min Act: -0.0000

Data Index: 719031 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1336480 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1885. Min Act: -0.0000

Data Index: 446074 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1342021 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1913. Min Act: -0.0000

Data Index: 590030 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.2958. Min Range: -0.2958

Max Act: 0.1832. Min Act: -0.0000

Data Index: 246012 (C4 (Web Text))

Max Activating Token Index: 228