Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4562 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2732. Min Act: -0.0002

Data Index: 498932 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2459. Min Act: -0.0001

Data Index: 181793 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2361. Min Act: -0.0002

Data Index: 874301 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2637. Min Act: -0.0001

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2494. Min Act: -0.0001

Data Index: 1209488 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2363. Min Act: -0.0001

Data Index: 737688 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2267. Min Act: -0.0001

Data Index: 642043 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1889. Min Act: -0.0001

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1862. Min Act: -0.0001

Data Index: 880124 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2030. Min Act: -0.0001

Data Index: 547170 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1803. Min Act: -0.0001

Data Index: 533587 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1906. Min Act: -0.0002

Data Index: 1248127 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1771. Min Act: -0.0001

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1337981 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1183030 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1814. Min Act: -0.0001

Data Index: 713954 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1698. Min Act: -0.0002

Data Index: 958330 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1031662 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1674. Min Act: -0.0001

Data Index: 699082 (C4 (Web Text))

Max Activating Token Index: 484