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

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

Neuron 4248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1288317 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1476250 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1060522 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1313059 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1009. Min Act: -0.0000

Data Index: 146619 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0928. Min Act: 0.0000

Data Index: 851718 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1011. Min Act: -0.0000

Data Index: 580920 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0965. Min Act: -0.0000

Data Index: 509135 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1385550 (Python Code)

Max Activating Token Index: 129

Text #9

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0793. Min Act: -0.0000

Data Index: 28128 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0839. Min Act: 0.0001

Data Index: 219903 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0831. Min Act: -0.0000

Data Index: 49585 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0952. Min Act: -0.0000

Data Index: 492303 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0826. Min Act: -0.0000

Data Index: 18248 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1177249 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1480016 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1646845 (Python Code)

Max Activating Token Index: 679

Text #17

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1059707 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0799. Min Act: -0.0000

Data Index: 164186 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1329869 (C4 (Web Text))

Max Activating Token Index: 604