Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5093 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4447. Min Act: -0.0001

Data Index: 174156 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1069254 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4662. Min Act: -0.0001

Data Index: 517924 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4271. Min Act: -0.0002

Data Index: 845454 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4190. Min Act: -0.0001

Data Index: 1114650 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4036. Min Act: -0.0001

Data Index: 344838 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1222507 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4315. Min Act: -0.0001

Data Index: 79487 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3868. Min Act: -0.0001

Data Index: 386012 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3654. Min Act: -0.0001

Data Index: 1062773 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1204583 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3508. Min Act: -0.0001

Data Index: 364521 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3829. Min Act: -0.0001

Data Index: 973304 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3807. Min Act: -0.0001

Data Index: 304840 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3870. Min Act: -0.0001

Data Index: 412452 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4126. Min Act: -0.0001

Data Index: 519794 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4183. Min Act: -0.0001

Data Index: 798933 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1021556 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.4135. Min Act: -0.0001

Data Index: 419047 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.4662. Min Range: -0.4662

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1244061 (C4 (Web Text))

Max Activating Token Index: 73