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

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

Neuron 51 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1523470 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0748. Min Act: -0.0002

Data Index: 278034 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0735. Min Act: -0.0002

Data Index: 85796 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1001103 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1474595 (Python Code)

Max Activating Token Index: 726

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1419123 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1570627 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1655785 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1427962 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1631959 (Python Code)

Max Activating Token Index: 465

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1403735 (Python Code)

Max Activating Token Index: 843

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1621007 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1578169 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1434458 (Python Code)

Max Activating Token Index: 611

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1436202 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1650192 (Python Code)

Max Activating Token Index: 357

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1636792 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1504451 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1638093 (Python Code)

Max Activating Token Index: 353

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1446681 (Python Code)

Max Activating Token Index: 429