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

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

Neuron 1404 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0876. Min Act: -0.0003

Data Index: 1449203 (Python Code)

Max Activating Token Index: 782

Text #1

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0842. Min Act: -0.0003

Data Index: 1616092 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1582993 (Python Code)

Max Activating Token Index: 712

Text #3

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0740. Min Act: -0.0003

Data Index: 1447456 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0722. Min Act: -0.0002

Data Index: 17467 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1648715 (Python Code)

Max Activating Token Index: 514

Text #6

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1635053 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0631. Min Act: -0.0002

Data Index: 365140 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1572876 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0589. Min Act: -0.0002

Data Index: 979697 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1485762 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1603227 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1002936 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1008023 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0588. Min Act: -0.0003

Data Index: 799238 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1639706 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0576. Min Act: -0.0002

Data Index: 328772 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0574. Min Act: -0.0003

Data Index: 333109 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0570. Min Act: -0.0003

Data Index: 684323 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0557. Min Act: -0.0003

Data Index: 587320 (C4 (Web Text))

Max Activating Token Index: 114