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

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

Neuron 3860 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: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 982364 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1369124 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1403997 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 393786 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 75657 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 525497 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0002

Data Index: 748510 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0003

Data Index: 225373 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1412198 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1404832 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1515257 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1449548 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1367085 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1606460 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1566097 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 536971 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 267573 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0003

Data Index: 168789 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0002

Data Index: 449701 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0698. Min Act: -0.0003

Data Index: 679855 (C4 (Web Text))

Max Activating Token Index: 1