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

Dataset: The Pile

Neuron 2610 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.7751. Min Act: -0.0000

Data Index: 1199502 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.5812. Min Act: -0.0000

Data Index: 977328 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.1321. Min Act: -0.0000

Data Index: 549976 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.1055. Min Act: -0.0000

Data Index: 1140233 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.9548. Min Act: -0.0000

Data Index: 1460925 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.0476. Min Act: -0.0000

Data Index: 1512178 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.0492. Min Act: -0.0000

Data Index: 1310645 (The Pile)

Max Activating Token Index: 14

Text #7

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.4721. Min Act: -0.0000

Data Index: 1423016 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.9615. Min Act: -0.0000

Data Index: 1661451 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.9493. Min Act: -0.0000

Data Index: 769407 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.7746. Min Act: -0.0000

Data Index: 1307604 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.9672. Min Act: -0.0000

Data Index: 1783923 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.9304. Min Act: -0.0000

Data Index: 1392086 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.0804. Min Act: -0.0000

Data Index: 1961616 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.9091. Min Act: -0.0000

Data Index: 1198599 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.8908. Min Act: -0.0000

Data Index: 1802286 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 4.7751. Min Range: -4.7751

Max Act: 4.0397. Min Act: -0.0000

Data Index: 1475088 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.7055. Min Act: -0.0000

Data Index: 863995 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.8620. Min Act: -0.0000

Data Index: 1240374 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 4.7751. Min Range: -4.7751

Max Act: 3.6670. Min Act: -0.0000

Data Index: 1635564 (The Pile)

Max Activating Token Index: 601