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

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

Neuron 4795 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: 0.0086. Min Range: -0.0086

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1599754 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1453383 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1494931 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1362831 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1614198 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0082. Min Act: -0.0002

Data Index: 1102430 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1601477 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1379923 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1564340 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0080. Min Act: -0.0002

Data Index: 384238 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1620863 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1410874 (Python Code)

Max Activating Token Index: 90

Text #12

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1456574 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1535299 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1450462 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1653841 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0076. Min Act: -0.0002

Data Index: 849947 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1451077 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1096581 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1654097 (Python Code)

Max Activating Token Index: 49