Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1033 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0741. Min Act: -0.0004

Data Index: 313416 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0004

Data Index: 590064 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0741. Min Act: -0.0004

Data Index: 395130 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0636. Min Act: -0.0004

Data Index: 219116 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0733. Min Act: -0.0004

Data Index: 797694 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0676. Min Act: -0.0004

Data Index: 297504 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0673. Min Act: -0.0004

Data Index: 865875 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0742. Min Act: -0.0004

Data Index: 1248645 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0655. Min Act: -0.0004

Data Index: 367347 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0680. Min Act: -0.0004

Data Index: 632168 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0702. Min Act: -0.0004

Data Index: 1284405 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0638. Min Act: -0.0004

Data Index: 1069983 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0662. Min Act: -0.0004

Data Index: 31873 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0670. Min Act: -0.0004

Data Index: 68898 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0642. Min Act: -0.0004

Data Index: 1030129 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0623. Min Act: -0.0004

Data Index: 724999 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0695. Min Act: -0.0004

Data Index: 707839 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0665. Min Act: -0.0004

Data Index: 387948 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0616. Min Act: -0.0004

Data Index: 434053 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0615. Min Act: -0.0004

Data Index: 1313404 (C4 (Web Text))

Max Activating Token Index: 319