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

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

Neuron 2852 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: 0.1372. Min Range: -0.1372

Max Act: 0.1372. Min Act: -0.0003

Data Index: 1468990 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1623888 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.1003. Min Act: -0.0002

Data Index: 17115 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1586006 (Python Code)

Max Activating Token Index: 937

Text #4

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0936. Min Act: -0.0003

Data Index: 1616888 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1415269 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0820. Min Act: -0.0002

Data Index: 601520 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1490762 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1117935 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0783. Min Act: -0.0003

Data Index: 158641 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1367647 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1549059 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1577098 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1289551 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1594189 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0723. Min Act: -0.0003

Data Index: 615352 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1591643 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0742. Min Act: -0.0003

Data Index: 641946 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1512241 (Python Code)

Max Activating Token Index: 685

Text #19

Max Range: 0.1372. Min Range: -0.1372

Max Act: 0.0727. Min Act: -0.0003

Data Index: 1371134 (Python Code)

Max Activating Token Index: 618