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

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

Neuron 3173 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1177. Min Act: -0.0002

Data Index: 753827 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1100. Min Act: -0.0002

Data Index: 60552 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1108. Min Act: -0.0002

Data Index: 932170 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1066. Min Act: -0.0002

Data Index: 451225 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1026. Min Act: -0.0002

Data Index: 135205 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1012. Min Act: -0.0002

Data Index: 708398 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1135383 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1006713 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0975. Min Act: -0.0002

Data Index: 1055589 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0975. Min Act: -0.0002

Data Index: 774887 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1039313 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1010. Min Act: -0.0002

Data Index: 102967 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0955. Min Act: -0.0002

Data Index: 933659 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0957. Min Act: -0.0002

Data Index: 328247 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0972. Min Act: -0.0002

Data Index: 545735 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1018349 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0953. Min Act: -0.0002

Data Index: 1025151 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1336853 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0940. Min Act: -0.0002

Data Index: 299723 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0925. Min Act: -0.0002

Data Index: 815960 (C4 (Web Text))

Max Activating Token Index: 41