Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 50 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1080444 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1027. Min Act: -0.0001

Data Index: 740332 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0977. Min Act: -0.0001

Data Index: 11626 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0966. Min Act: -0.0001

Data Index: 58409 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1265681 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1266352 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0925. Min Act: -0.0001

Data Index: 574904 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1347193 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0912. Min Act: -0.0001

Data Index: 236317 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0911. Min Act: -0.0001

Data Index: 118975 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0911. Min Act: -0.0001

Data Index: 307024 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0946. Min Act: -0.0001

Data Index: 79522 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0901. Min Act: -0.0001

Data Index: 205759 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0901. Min Act: -0.0001

Data Index: 356326 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0936. Min Act: -0.0001

Data Index: 757905 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0882. Min Act: -0.0001

Data Index: 615497 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0846. Min Act: -0.0001

Data Index: 292748 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1197338 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0867. Min Act: -0.0001

Data Index: 63064 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0865. Min Act: -0.0001

Data Index: 954190 (C4 (Web Text))

Max Activating Token Index: 502