Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 699 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0002

Data Index: 225369 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0701. Min Act: -0.0002

Data Index: 488078 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0668. Min Act: -0.0002

Data Index: 480313 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1199624 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1057549 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0628. Min Act: -0.0002

Data Index: 614738 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0631. Min Act: -0.0002

Data Index: 115515 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0634. Min Act: -0.0002

Data Index: 793631 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0623. Min Act: -0.0002

Data Index: 948664 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1380028 (Python Code)

Max Activating Token Index: 626

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0626. Min Act: -0.0002

Data Index: 539450 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0602. Min Act: -0.0002

Data Index: 24506 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1445934 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0593. Min Act: -0.0002

Data Index: 622753 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1076552 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1188414 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0592. Min Act: -0.0002

Data Index: 256321 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1206686 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0592. Min Act: -0.0002

Data Index: 53595 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1641662 (Python Code)

Max Activating Token Index: 25