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

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

Neuron 4479 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1045. Min Act: -0.0001

Data Index: 99710 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1334312 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0994. Min Act: -0.0000

Data Index: 281531 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1002. Min Act: -0.0000

Data Index: 250942 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0871. Min Act: -0.0000

Data Index: 40604 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0902. Min Act: -0.0001

Data Index: 141585 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0890. Min Act: -0.0000

Data Index: 369078 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0948. Min Act: -0.0001

Data Index: 240350 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0840. Min Act: -0.0001

Data Index: 373096 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1027922 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0864. Min Act: -0.0000

Data Index: 36503 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1282970 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0833. Min Act: -0.0000

Data Index: 336170 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0831. Min Act: -0.0001

Data Index: 258914 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1238776 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0848. Min Act: -0.0001

Data Index: 246954 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0811. Min Act: -0.0000

Data Index: 987808 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1185381 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0756. Min Act: -0.0001

Data Index: 682899 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0815. Min Act: -0.0001

Data Index: 60179 (C4 (Web Text))

Max Activating Token Index: 252