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

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

Neuron 4863 in Layer 0

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: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1426002 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1630331 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1504571 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1638608 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1379495 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1504515 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1537234 (Python Code)

Max Activating Token Index: 531

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1612215 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1386850 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1405226 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1618134 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1606004 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1576798 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1508166 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1585149 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1445439 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1426805 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1460460 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1625158 (Python Code)

Max Activating Token Index: 272

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1395832 (Python Code)

Max Activating Token Index: 317