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

Dataset: The Pile

Neuron 2071 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: 3.7507. Min Range: -3.7507

Max Act: 3.4416. Min Act: -0.0000

Data Index: 1699433 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.7507. Min Act: -0.0000

Data Index: 805664 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.4854. Min Act: -0.0000

Data Index: 1088076 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.3644. Min Act: -0.0000

Data Index: 205713 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.3146. Min Act: -0.0000

Data Index: 1531393 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1267389 (The Pile)

Max Activating Token Index: 818

Text #6

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0908. Min Act: -0.0000

Data Index: 1718421 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.2121. Min Act: -0.0000

Data Index: 887297 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.2131. Min Act: -0.0000

Data Index: 1734489 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1912. Min Act: -0.0000

Data Index: 1535588 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1587. Min Act: -0.0000

Data Index: 1910105 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1549. Min Act: -0.0000

Data Index: 223027 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1221. Min Act: -0.0000

Data Index: 1645364 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1095. Min Act: -0.0000

Data Index: 7273 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1012. Min Act: -0.0000

Data Index: 1009413 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0840. Min Act: -0.0000

Data Index: 790205 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0474. Min Act: -0.0000

Data Index: 674888 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 3.7507. Min Range: -3.7507

Max Act: 2.7425. Min Act: -0.0000

Data Index: 1534468 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.1717. Min Act: -0.0000

Data Index: 583479 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 3.7507. Min Range: -3.7507

Max Act: 3.0030. Min Act: -0.0000

Data Index: 1086253 (The Pile)

Max Activating Token Index: 534