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

Dataset: The Pile

Neuron 4563 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.9515. Min Act: -0.0000

Data Index: 227758 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1318140 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1753399 (The Pile)

Max Activating Token Index: 514

Text #3

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.8492. Min Act: -0.0000

Data Index: 923725 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1569051 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.8486. Min Act: -0.0000

Data Index: 450601 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1328260 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1906973 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1019446 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1842167 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6513. Min Act: -0.0000

Data Index: 614102 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6454. Min Act: -0.0000

Data Index: 794283 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.8263. Min Act: -0.0000

Data Index: 480850 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1635357 (The Pile)

Max Activating Token Index: 829

Text #14

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.6360. Min Act: -0.0000

Data Index: 564964 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.5908. Min Act: -0.0000

Data Index: 149668 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.5244. Min Act: -0.0000

Data Index: 785893 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1443389 (The Pile)

Max Activating Token Index: 740

Text #18

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.5211. Min Act: 0.0000

Data Index: 760083 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 0.9515. Min Range: -0.9515

Max Act: 0.4942. Min Act: 0.0000

Data Index: 767840 (The Pile)

Max Activating Token Index: 491