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

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

Neuron 4624 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: 0.2167. Min Range: -0.2167

Max Act: 0.2167. Min Act: -0.0001

Data Index: 1368865 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1403998 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1645067 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1589355 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1420351 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1391157 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1810. Min Act: -0.0001

Data Index: 1656985 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1766. Min Act: -0.0001

Data Index: 1571226 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1777. Min Act: -0.0001

Data Index: 1649298 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1716. Min Act: -0.0001

Data Index: 1391382 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1612910 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1442129 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1747. Min Act: -0.0002

Data Index: 1445430 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1603089 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1535843 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1624979 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1553575 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1420252 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1591050 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.2167. Min Range: -0.2167

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1573259 (Python Code)

Max Activating Token Index: 1023