Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1201 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0002

Data Index: 21091 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1635427 (Python Code)

Max Activating Token Index: 963

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0689. Min Act: -0.0002

Data Index: 650368 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1377799 (Python Code)

Max Activating Token Index: 174

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0616. Min Act: -0.0002

Data Index: 335247 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0664. Min Act: -0.0003

Data Index: 815701 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1585504 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0652. Min Act: -0.0002

Data Index: 681684 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0624. Min Act: -0.0002

Data Index: 754738 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1606016 (Python Code)

Max Activating Token Index: 550

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0605. Min Act: -0.0002

Data Index: 990585 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1421361 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1589237 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1623578 (Python Code)

Max Activating Token Index: 637

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0618. Min Act: -0.0002

Data Index: 987556 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1566685 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1577844 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0605. Min Act: -0.0002

Data Index: 759505 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1608022 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1555535 (Python Code)

Max Activating Token Index: 95