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

Dataset: The Pile

Neuron 3221 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0616. Min Range: -1.0616

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1029005 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9619. Min Act: -0.0000

Data Index: 543841 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1377885 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 1.0616. Min Range: -1.0616

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1055027 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9627. Min Act: -0.0000

Data Index: 953635 (The Pile)

Max Activating Token Index: 609

Text #5

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1811395 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8601. Min Act: -0.0000

Data Index: 279172 (The Pile)

Max Activating Token Index: 614

Text #7

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1530945 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1632561 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9063. Min Act: -0.0000

Data Index: 361899 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1587999 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1770152 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8552. Min Act: -0.0000

Data Index: 322003 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1090065 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1717536 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1589585 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8227. Min Act: -0.0000

Data Index: 163986 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8093. Min Act: -0.0000

Data Index: 713265 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1744359 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1088902 (The Pile)

Max Activating Token Index: 665