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

Dataset: The Pile

Neuron 415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1903. Min Range: -3.1903

Max Act: 3.1871. Min Act: -0.0000

Data Index: 1343230 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.9444. Min Act: -0.0000

Data Index: 851732 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 3.1903. Min Range: -3.1903

Max Act: 3.1903. Min Act: -0.0000

Data Index: 1536004 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.9623. Min Act: -0.0000

Data Index: 1094841 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.5294. Min Act: -0.0000

Data Index: 169792 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.8972. Min Act: -0.0000

Data Index: 85504 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3528. Min Act: -0.0000

Data Index: 739018 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.4808. Min Act: -0.0000

Data Index: 526965 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.4353. Min Act: -0.0000

Data Index: 1020923 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.6231. Min Act: -0.0000

Data Index: 1393071 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.1325. Min Act: -0.0000

Data Index: 1196588 (The Pile)

Max Activating Token Index: 44

Text #11

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.3695. Min Act: -0.0000

Data Index: 1055260 (The Pile)

Max Activating Token Index: 770

Text #12

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9480. Min Act: -0.0000

Data Index: 1736502 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.1353. Min Act: -0.0000

Data Index: 1753735 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0376. Min Act: -0.0000

Data Index: 326690 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 3.1903. Min Range: -3.1903

Max Act: 1.9122. Min Act: -0.0000

Data Index: 503941 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.4406. Min Act: -0.0000

Data Index: 512899 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.2070. Min Act: -0.0000

Data Index: 1098517 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0635. Min Act: -0.0000

Data Index: 343201 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 3.1903. Min Range: -3.1903

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1363233 (The Pile)

Max Activating Token Index: 100