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

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

Neuron 1061 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 179371 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1236472 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1022 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1204910 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1070596 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1325098 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0621. Min Act: -0.0002

Data Index: 550840 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0602. Min Act: -0.0002

Data Index: 459688 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0598. Min Act: -0.0002

Data Index: 362316 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0576. Min Act: -0.0002

Data Index: 85082 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0597. Min Act: -0.0002

Data Index: 423855 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0618. Min Act: -0.0002

Data Index: 961290 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1275495 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0591. Min Act: -0.0002

Data Index: 292493 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0596. Min Act: -0.0002

Data Index: 425990 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0588. Min Act: -0.0002

Data Index: 314163 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0583. Min Act: -0.0002

Data Index: 760982 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0581. Min Act: -0.0002

Data Index: 331479 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0577. Min Act: -0.0002

Data Index: 886734 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0574. Min Act: -0.0002

Data Index: 489263 (C4 (Web Text))

Max Activating Token Index: 670