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

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

Neuron 71 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0000

Data Index: 90854 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0773. Min Act: -0.0000

Data Index: 252417 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1112752 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0672. Min Act: -0.0000

Data Index: 995314 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0701. Min Act: -0.0000

Data Index: 466253 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0692. Min Act: -0.0000

Data Index: 405456 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0634. Min Act: -0.0000

Data Index: 633324 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1175638 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0639. Min Act: -0.0000

Data Index: 608931 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0644. Min Act: -0.0000

Data Index: 303350 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0604. Min Act: -0.0000

Data Index: 385949 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1072421 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0571. Min Act: -0.0000

Data Index: 369219 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0634. Min Act: -0.0000

Data Index: 325295 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0588. Min Act: -0.0000

Data Index: 479388 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1176798 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0588. Min Act: -0.0000

Data Index: 115929 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0580. Min Act: -0.0000

Data Index: 281181 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0597. Min Act: -0.0000

Data Index: 423572 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1236829 (C4 (Web Text))

Max Activating Token Index: 700