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

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

Neuron 219 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: 0.1022. Min Range: -0.1022

Max Act: 0.1022. Min Act: -0.0005

Data Index: 163263 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0985. Min Act: -0.0005

Data Index: 660534 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0970. Min Act: -0.0005

Data Index: 1081409 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0920. Min Act: -0.0005

Data Index: 402789 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0917. Min Act: -0.0005

Data Index: 360951 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0886. Min Act: -0.0005

Data Index: 1037716 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0927. Min Act: -0.0005

Data Index: 1156303 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0936. Min Act: -0.0005

Data Index: 474063 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0963. Min Act: -0.0005

Data Index: 1186698 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0935. Min Act: -0.0005

Data Index: 1347418 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0931. Min Act: -0.0005

Data Index: 1063743 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0916. Min Act: -0.0005

Data Index: 563977 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0887. Min Act: -0.0005

Data Index: 894008 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0860. Min Act: -0.0005

Data Index: 254826 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0910. Min Act: -0.0005

Data Index: 112691 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0877. Min Act: -0.0005

Data Index: 561949 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0810. Min Act: -0.0005

Data Index: 717946 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0883. Min Act: -0.0005

Data Index: 1311916 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0845. Min Act: -0.0005

Data Index: 873694 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0866. Min Act: -0.0005

Data Index: 1022932 (C4 (Web Text))

Max Activating Token Index: 87