Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3012 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1017935 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1922. Min Act: -0.0000

Data Index: 573375 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1892. Min Act: -0.0000

Data Index: 146783 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1421635 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1180267 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1747. Min Act: -0.0000

Data Index: 184388 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1632733 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1749. Min Act: -0.0000

Data Index: 598950 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1713. Min Act: -0.0000

Data Index: 192460 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1036558 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1631. Min Act: -0.0000

Data Index: 189774 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1458. Min Act: -0.0000

Data Index: 77985 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1573. Min Act: -0.0000

Data Index: 89015 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1175794 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1679. Min Act: -0.0000

Data Index: 773797 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1243880 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1515. Min Act: -0.0000

Data Index: 279623 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1082469 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1456792 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.1922. Min Range: -0.1922

Max Act: 0.1632. Min Act: -0.0000

Data Index: 881682 (The Pile)

Max Activating Token Index: 829