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

Dataset: The Pile

Neuron 3027 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.2754. Min Act: -0.0000

Data Index: 1931006 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1404089 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.2925. Min Act: -0.0000

Data Index: 306952 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.1872. Min Act: -0.0000

Data Index: 644735 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.0904. Min Act: -0.0000

Data Index: 93450 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1706552 (The Pile)

Max Activating Token Index: 657

Text #6

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.0828. Min Act: -0.0000

Data Index: 221561 (The Pile)

Max Activating Token Index: 810

Text #7

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.1006. Min Act: -0.0000

Data Index: 615712 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.0013. Min Act: -0.0000

Data Index: 42076 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9601. Min Act: -0.0000

Data Index: 873039 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1530230 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1842883 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1790795 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9648. Min Act: -0.0000

Data Index: 930034 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1395006 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1551007 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9498. Min Act: -0.0000

Data Index: 735741 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9534. Min Act: -0.0000

Data Index: 1419429 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9105. Min Act: -0.0000

Data Index: 329529 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9047. Min Act: -0.0000

Data Index: 844790 (The Pile)

Max Activating Token Index: 674