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

Dataset: The Pile

Neuron 3492 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: 1.8486. Min Range: -1.8486

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1565653 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.7069. Min Act: -0.0000

Data Index: 927908 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.8486. Min Act: -0.0000

Data Index: 900033 (The Pile)

Max Activating Token Index: 719

Text #3

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1870208 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.6266. Min Act: -0.0000

Data Index: 229742 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.6399. Min Act: -0.0000

Data Index: 965703 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1305329 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.6928. Min Act: -0.0000

Data Index: 511015 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.5388. Min Act: -0.0000

Data Index: 173158 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1441284 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.5529. Min Act: -0.0000

Data Index: 1244358 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4720. Min Act: -0.0000

Data Index: 125071 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.5090. Min Act: -0.0000

Data Index: 330700 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4448. Min Act: -0.0000

Data Index: 1373527 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4357. Min Act: -0.0000

Data Index: 596601 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1756752 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4772. Min Act: -0.0000

Data Index: 255032 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1361792 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4173. Min Act: -0.0000

Data Index: 798810 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3929. Min Act: -0.0000

Data Index: 68929 (The Pile)

Max Activating Token Index: 693