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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2172 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3879. Min Range: -3.3879

Max Act: 3.3879. Min Act: -0.0000

Data Index: 774335 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.8688. Min Act: -0.0000

Data Index: 1103821 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.7808. Min Act: -0.0000

Data Index: 1340134 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.7107. Min Act: -0.0000

Data Index: 563768 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.7540. Min Act: -0.0000

Data Index: 187081 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.7291. Min Act: -0.0000

Data Index: 402130 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.8603. Min Act: -0.0000

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.7006. Min Act: -0.0000

Data Index: 1315164 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.5239. Min Act: -0.0000

Data Index: 638287 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.3063. Min Act: -0.0000

Data Index: 71688 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.1934. Min Act: -0.0000

Data Index: 1102572 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.2521. Min Act: -0.0000

Data Index: 651579 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.0001. Min Act: -0.0000

Data Index: 376249 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 3.3879. Min Range: -3.3879

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1105203 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 3.3879. Min Range: -3.3879

Max Act: 1.9415. Min Act: -0.0000

Data Index: 729524 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 3.3879. Min Range: -3.3879

Max Act: 1.8245. Min Act: -0.0000

Data Index: 650794 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 3.3879. Min Range: -3.3879

Max Act: 1.9189. Min Act: -0.0000

Data Index: 575182 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 3.3879. Min Range: -3.3879

Max Act: 1.9902. Min Act: -0.0000

Data Index: 994228 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 3.3879. Min Range: -3.3879

Max Act: 1.9646. Min Act: -0.0000

Data Index: 110966 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 3.3879. Min Range: -3.3879

Max Act: 1.8381. Min Act: -0.0000

Data Index: 765242 (C4 (Web Text))

Max Activating Token Index: 372