Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 808 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0826. Min Act: -0.0006

Data Index: 1312237 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0006

Data Index: 75739 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0768. Min Act: -0.0006

Data Index: 1024128 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0763. Min Act: -0.0006

Data Index: 777119 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0750. Min Act: -0.0006

Data Index: 386411 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0717. Min Act: -0.0006

Data Index: 304779 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0713. Min Act: -0.0006

Data Index: 764162 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0710. Min Act: -0.0006

Data Index: 147757 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0679. Min Act: -0.0006

Data Index: 814111 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0695. Min Act: -0.0006

Data Index: 151597 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0690. Min Act: -0.0006

Data Index: 66779 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0689. Min Act: -0.0006

Data Index: 1174618 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0657. Min Act: -0.0006

Data Index: 483858 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0649. Min Act: -0.0006

Data Index: 1307945 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0678. Min Act: -0.0006

Data Index: 445935 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0701. Min Act: -0.0006

Data Index: 26698 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0673. Min Act: -0.0006

Data Index: 290964 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0667. Min Act: -0.0006

Data Index: 69410 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0665. Min Act: -0.0006

Data Index: 937420 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0662. Min Act: -0.0006

Data Index: 1051341 (C4 (Web Text))

Max Activating Token Index: 308