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

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

Neuron 140 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0843. Min Act: -0.0002

Data Index: 933341 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0876. Min Act: -0.0002

Data Index: 214878 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1283936 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0940. Min Act: -0.0002

Data Index: 702116 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0829. Min Act: -0.0002

Data Index: 874399 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0749. Min Act: -0.0002

Data Index: 155443 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0718. Min Act: -0.0002

Data Index: 553995 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0758. Min Act: -0.0002

Data Index: 206358 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0741. Min Act: -0.0002

Data Index: 4522 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1068933 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0785. Min Act: -0.0002

Data Index: 407520 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0727. Min Act: -0.0002

Data Index: 835292 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0704. Min Act: -0.0002

Data Index: 492362 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0722. Min Act: -0.0002

Data Index: 218374 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0663. Min Act: -0.0002

Data Index: 184831 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1330798 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0689. Min Act: -0.0002

Data Index: 40331 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0655. Min Act: -0.0002

Data Index: 657277 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1067107 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.0940. Min Range: -0.0940

Max Act: 0.0682. Min Act: -0.0002

Data Index: 617033 (C4 (Web Text))

Max Activating Token Index: 972