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

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

Neuron 998 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1454649 (Python Code)

Max Activating Token Index: 604

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0449. Min Act: -0.0002

Data Index: 543947 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1610388 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0457. Min Act: -0.0002

Data Index: 334341 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0393. Min Act: -0.0002

Data Index: 389912 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0447. Min Act: -0.0002

Data Index: 949660 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1072784 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0419. Min Act: -0.0002

Data Index: 800965 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0409. Min Act: -0.0002

Data Index: 82141 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0428. Min Act: -0.0002

Data Index: 481438 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1376059 (Python Code)

Max Activating Token Index: 765

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1069156 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1233915 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1510813 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1555418 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0392. Min Act: -0.0002

Data Index: 29451 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0389. Min Act: -0.0002

Data Index: 796959 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1200099 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1493067 (Python Code)

Max Activating Token Index: 202

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0394. Min Act: -0.0002

Data Index: 586692 (C4 (Web Text))

Max Activating Token Index: 34