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

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

Neuron 3848 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: 0.8733. Min Range: -0.8733

Max Act: 0.8733. Min Act: -0.0000

Data Index: 688102 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7575. Min Act: -0.0000

Data Index: 290520 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1361310 (Python Code)

Max Activating Token Index: 938

Text #3

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1529529 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7417. Min Act: -0.0000

Data Index: 43590 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1509606 (Python Code)

Max Activating Token Index: 589

Text #6

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1653725 (Python Code)

Max Activating Token Index: 947

Text #7

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1112497 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6946. Min Act: -0.0000

Data Index: 207790 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1346390 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6805. Min Act: -0.0000

Data Index: 736911 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1385686 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1533738 (Python Code)

Max Activating Token Index: 274

Text #13

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1191766 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6879. Min Act: -0.0000

Data Index: 410154 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1201440 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7193. Min Act: -0.0000

Data Index: 739195 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6662. Min Act: -0.0000

Data Index: 211856 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1245047 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1520645 (Python Code)

Max Activating Token Index: 618