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

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

Neuron 1409 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: 0.5900. Min Range: -0.5900

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1608865 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1626139 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5185. Min Act: -0.0001

Data Index: 1517715 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5108. Min Act: -0.0002

Data Index: 1372276 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5115. Min Act: -0.0001

Data Index: 1548037 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1642462 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4993. Min Act: -0.0001

Data Index: 1403706 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4854. Min Act: -0.0002

Data Index: 1607184 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4984. Min Act: -0.0001

Data Index: 1650010 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4973. Min Act: -0.0001

Data Index: 1637344 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4871. Min Act: -0.0001

Data Index: 1458819 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4783. Min Act: -0.0002

Data Index: 1500883 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4720. Min Act: -0.0001

Data Index: 1451836 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4793. Min Act: -0.0002

Data Index: 1388798 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1463411 (Python Code)

Max Activating Token Index: 432

Text #15

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4710. Min Act: -0.0001

Data Index: 1506981 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4734. Min Act: -0.0002

Data Index: 1459925 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4695. Min Act: -0.0002

Data Index: 1534831 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4671. Min Act: -0.0001

Data Index: 1372943 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.5900. Min Range: -0.5900

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1540537 (Python Code)

Max Activating Token Index: 15