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

Dataset: The Pile

Neuron 2465 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.7507. Min Act: -0.0000

Data Index: 1321452 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1613781 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1793238 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4052. Min Act: -0.0000

Data Index: 1149345 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.3791. Min Act: -0.0000

Data Index: 993731 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1772207 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5111. Min Act: -0.0000

Data Index: 666639 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4178. Min Act: -0.0000

Data Index: 815329 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4103. Min Act: -0.0000

Data Index: 1852162 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1269080 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.3676. Min Act: -0.0000

Data Index: 283458 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5433. Min Act: -0.0000

Data Index: 1521674 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.3730. Min Act: -0.0000

Data Index: 800992 (The Pile)

Max Activating Token Index: 385

Text #13

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1807700 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4449. Min Act: -0.0000

Data Index: 647937 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1125958 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4064. Min Act: -0.0000

Data Index: 1257816 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1084097 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.1836. Min Act: -0.0000

Data Index: 60427 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1782307 (The Pile)

Max Activating Token Index: 682