Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 803 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0005

Data Index: 1083458 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0748. Min Act: -0.0005

Data Index: 303698 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0707. Min Act: -0.0005

Data Index: 1109949 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0690. Min Act: -0.0005

Data Index: 672830 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0660. Min Act: -0.0005

Data Index: 805642 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0641. Min Act: -0.0005

Data Index: 214294 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0654. Min Act: -0.0005

Data Index: 568999 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0603. Min Act: -0.0005

Data Index: 1346368 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0633. Min Act: -0.0005

Data Index: 546358 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0607. Min Act: -0.0005

Data Index: 735758 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0623. Min Act: -0.0005

Data Index: 1063918 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0572. Min Act: -0.0005

Data Index: 180796 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0636. Min Act: -0.0005

Data Index: 1229877 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0636. Min Act: -0.0005

Data Index: 492495 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0636. Min Act: -0.0005

Data Index: 1319225 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0591. Min Act: -0.0005

Data Index: 1094860 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0609. Min Act: -0.0005

Data Index: 1083830 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0574. Min Act: -0.0005

Data Index: 275952 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0607. Min Act: -0.0005

Data Index: 115017 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0585. Min Act: -0.0005

Data Index: 616731 (C4 (Web Text))

Max Activating Token Index: 439