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

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

Neuron 29 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: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0002

Data Index: 130399 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0841. Min Act: -0.0003

Data Index: 510869 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0840. Min Act: -0.0002

Data Index: 595864 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0828. Min Act: -0.0002

Data Index: 832706 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0819. Min Act: -0.0002

Data Index: 190361 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0805. Min Act: -0.0002

Data Index: 525760 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0773. Min Act: -0.0002

Data Index: 813345 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0796. Min Act: -0.0002

Data Index: 286212 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1302488 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1044642 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1194086 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1206435 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0758. Min Act: -0.0002

Data Index: 237763 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0772. Min Act: -0.0002

Data Index: 120033 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1108962 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1064435 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1180965 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0748. Min Act: -0.0002

Data Index: 31627 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0753. Min Act: -0.0002

Data Index: 515330 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0754. Min Act: -0.0002

Data Index: 913875 (C4 (Web Text))

Max Activating Token Index: 414