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

Dataset: The Pile

Neuron 3719 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0000

Data Index: 203036 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0519. Min Act: 0.0000

Data Index: 793476 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0434. Min Act: -0.0000

Data Index: 182578 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0429. Min Act: 0.0000

Data Index: 1009625 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0424. Min Act: -0.0000

Data Index: 593446 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0418. Min Act: 0.0000

Data Index: 666221 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1199046 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0409. Min Act: -0.0000

Data Index: 924456 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0405. Min Act: 0.0000

Data Index: 656977 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0384. Min Act: 0.0000

Data Index: 1062878 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0395. Min Act: 0.0000

Data Index: 1914659 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0379. Min Act: 0.0000

Data Index: 1888120 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0394. Min Act: 0.0000

Data Index: 1903283 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0394. Min Act: 0.0000

Data Index: 841786 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0394. Min Act: 0.0000

Data Index: 204462 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0393. Min Act: 0.0000

Data Index: 759248 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0392. Min Act: -0.0000

Data Index: 1362714 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0390. Min Act: 0.0000

Data Index: 1772140 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0388. Min Act: 0.0000

Data Index: 1266202 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0387. Min Act: 0.0000

Data Index: 1290736 (The Pile)

Max Activating Token Index: 1023