Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 361 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1538836 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1554108 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1469385 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1411400 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1649568 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1649202 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1553277 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1376708 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1419879 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1512870 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1491618 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1651328 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1574749 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1566746 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1467664 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1463863 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1518181 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1386435 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1380943 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1559477 (Python Code)

Max Activating Token Index: 1023