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

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

Neuron 3528 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0001

Data Index: 980242 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0918. Min Act: -0.0001

Data Index: 477831 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0689. Min Act: -0.0001

Data Index: 826322 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0584. Min Act: -0.0001

Data Index: 144893 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0645. Min Act: -0.0001

Data Index: 707266 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0675. Min Act: -0.0001

Data Index: 1364838 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0664. Min Act: -0.0001

Data Index: 442507 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1526545 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1399362 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1330889 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0634. Min Act: -0.0001

Data Index: 920202 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1442296 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0671. Min Act: -0.0001

Data Index: 853958 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1440894 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1558496 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1591119 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1117749 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1471159 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0544. Min Act: -0.0001

Data Index: 481973 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0578. Min Act: -0.0001

Data Index: 8760 (C4 (Web Text))

Max Activating Token Index: 465