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

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

Neuron 2192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1439055 (Python Code)

Max Activating Token Index: 917

Text #1

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0656. Min Act: -0.0002

Data Index: 497419 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1458517 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0663. Min Act: -0.0002

Data Index: 496119 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1567247 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1595262 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1511712 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0581. Min Act: -0.0002

Data Index: 447181 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1076357 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0624. Min Act: -0.0002

Data Index: 620230 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0580. Min Act: -0.0002

Data Index: 629687 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0568. Min Act: -0.0002

Data Index: 403403 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1545898 (Python Code)

Max Activating Token Index: 444

Text #13

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1038580 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1367963 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1587823 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1543278 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1488850 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0539. Min Act: -0.0002

Data Index: 832515 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1486595 (Python Code)

Max Activating Token Index: 2