Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 71 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0926. Min Act: -0.0001

Data Index: 777936 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0947. Min Act: -0.0001

Data Index: 923700 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0941. Min Act: -0.0001

Data Index: 29631 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1102410 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0862. Min Act: -0.0001

Data Index: 151423 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0838. Min Act: -0.0001

Data Index: 830306 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0789. Min Act: -0.0001

Data Index: 214861 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0868. Min Act: -0.0001

Data Index: 556743 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0680. Min Act: -0.0001

Data Index: 665027 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0751. Min Act: -0.0001

Data Index: 491957 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1260617 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1014586 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0736. Min Act: -0.0001

Data Index: 781978 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0610. Min Act: -0.0001

Data Index: 147432 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0707. Min Act: -0.0001

Data Index: 136612 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0638. Min Act: -0.0001

Data Index: 320925 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1354560 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0648. Min Act: -0.0001

Data Index: 689255 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0653. Min Act: -0.0001

Data Index: 240330 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1189236 (C4 (Web Text))

Max Activating Token Index: 933