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

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

Neuron 4988 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2621. Min Act: -0.0000

Data Index: 478213 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2144. Min Act: -0.0000

Data Index: 263283 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2142. Min Act: -0.0000

Data Index: 255741 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2213. Min Act: -0.0000

Data Index: 993838 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1090001 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.2046. Min Act: -0.0000

Data Index: 945487 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1917. Min Act: -0.0000

Data Index: 685910 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1970. Min Act: -0.0000

Data Index: 918951 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1958. Min Act: -0.0000

Data Index: 938443 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1954. Min Act: -0.0000

Data Index: 917438 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1224213 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1878. Min Act: -0.0000

Data Index: 112856 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1010625 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1829. Min Act: -0.0000

Data Index: 40773 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1788. Min Act: -0.0000

Data Index: 640648 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1855. Min Act: -0.0000

Data Index: 756138 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1730. Min Act: -0.0000

Data Index: 266502 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1106461 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1107435 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.2621. Min Range: -0.2621

Max Act: 0.1756. Min Act: -0.0000

Data Index: 382161 (C4 (Web Text))

Max Activating Token Index: 1005