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

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

Neuron 2255 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1618597 (Python Code)

Max Activating Token Index: 489

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0962. Min Act: -0.0001

Data Index: 486909 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0001

Data Index: 850594 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1597060 (Python Code)

Max Activating Token Index: 858

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1328196 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1283789 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1000. Min Act: -0.0000

Data Index: 116050 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1655188 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1465005 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0934. Min Act: -0.0001

Data Index: 492188 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0897. Min Act: -0.0001

Data Index: 612046 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1528329 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1393365 (Python Code)

Max Activating Token Index: 143

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0891. Min Act: -0.0000

Data Index: 453140 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1454050 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1064454 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1372634 (Python Code)

Max Activating Token Index: 849

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1648200 (Python Code)

Max Activating Token Index: 409

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1507374 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1387063 (Python Code)

Max Activating Token Index: 142