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

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

Neuron 1837 in Layer 1

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: 0.1101. Min Range: -0.1101

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1436245 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1542863 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1428157 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1002. Min Act: -0.0002

Data Index: 1545443 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1400599 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1632537 (Python Code)

Max Activating Token Index: 195

Text #6

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1516776 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1484640 (Python Code)

Max Activating Token Index: 765

Text #8

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1592469 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1599481 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1433093 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1515054 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1590460 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1504932 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1425211 (Python Code)

Max Activating Token Index: 541

Text #15

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1436067 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1468818 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1624583 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1428337 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1498752 (Python Code)

Max Activating Token Index: 158