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

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

Neuron 2864 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0827. Min Act: -0.0001

Data Index: 371191 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1253867 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0817. Min Act: -0.0001

Data Index: 581660 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1158751 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0712. Min Act: -0.0001

Data Index: 909619 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0736. Min Act: -0.0001

Data Index: 463832 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0643. Min Act: -0.0001

Data Index: 255142 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0602. Min Act: -0.0001

Data Index: 133915 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0673. Min Act: -0.0001

Data Index: 769647 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0621. Min Act: -0.0001

Data Index: 279213 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1026138 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0610. Min Act: -0.0001

Data Index: 610629 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0660. Min Act: -0.0001

Data Index: 577401 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0562. Min Act: -0.0001

Data Index: 483536 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0545. Min Act: -0.0001

Data Index: 7859 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0586. Min Act: -0.0001

Data Index: 199999 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0554. Min Act: -0.0001

Data Index: 145001 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1119924 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1263075 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0569. Min Act: -0.0001

Data Index: 472808 (C4 (Web Text))

Max Activating Token Index: 462