Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2733 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7695. Min Act: -0.0001

Data Index: 1016297 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6507. Min Act: -0.0000

Data Index: 829007 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5710. Min Act: -0.0000

Data Index: 588597 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5611. Min Act: -0.0000

Data Index: 57160 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5308. Min Act: 0.0001

Data Index: 774543 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5003. Min Act: -0.0000

Data Index: 38775 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4993. Min Act: -0.0000

Data Index: 697820 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4437. Min Act: 0.0001

Data Index: 587498 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5092. Min Act: 0.0001

Data Index: 265005 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5026. Min Act: 0.0001

Data Index: 658415 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5006. Min Act: -0.0001

Data Index: 1988 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4751. Min Act: -0.0000

Data Index: 208960 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4773. Min Act: -0.0000

Data Index: 224851 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4899. Min Act: -0.0001

Data Index: 1345965 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4925. Min Act: -0.0000

Data Index: 17132 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4725. Min Act: -0.0000

Data Index: 414223 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4899. Min Act: 0.0000

Data Index: 99219 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1253284 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4388. Min Act: 0.0000

Data Index: 1061769 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4413. Min Act: -0.0000

Data Index: 596899 (C4 (Web Text))

Max Activating Token Index: 39