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

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

Neuron 3117 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1050953 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0735. Min Act: -0.0002

Data Index: 909857 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0705. Min Act: -0.0002

Data Index: 893702 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0674. Min Act: -0.0001

Data Index: 428732 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1141526 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1113750 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0670. Min Act: -0.0002

Data Index: 698545 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0642. Min Act: -0.0001

Data Index: 68101 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1011537 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0626. Min Act: -0.0001

Data Index: 947994 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0614. Min Act: -0.0001

Data Index: 326898 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0571. Min Act: -0.0002

Data Index: 82187 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0588. Min Act: -0.0002

Data Index: 482854 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1227355 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1069993 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0613. Min Act: -0.0002

Data Index: 700344 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0550. Min Act: -0.0002

Data Index: 389982 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0591. Min Act: -0.0001

Data Index: 922145 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1192843 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0583. Min Act: -0.0002

Data Index: 875942 (C4 (Web Text))

Max Activating Token Index: 150