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

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

Neuron 425 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: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1530893 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1552460 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1405152 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1504712 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1656855 (Python Code)

Max Activating Token Index: 827

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1536073 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1440662 (Python Code)

Max Activating Token Index: 406

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1584375 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1365973 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1586024 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1548757 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1389255 (Python Code)

Max Activating Token Index: 923

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1552938 (Python Code)

Max Activating Token Index: 480

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1562716 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1390114 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1487048 (Python Code)

Max Activating Token Index: 464

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1371442 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1436852 (Python Code)

Max Activating Token Index: 798

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1625747 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1461831 (Python Code)

Max Activating Token Index: 356