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

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

Neuron 2968 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0001

Data Index: 789161 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0871. Min Act: -0.0001

Data Index: 781771 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1168847 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0792. Min Act: -0.0001

Data Index: 233700 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0810. Min Act: -0.0001

Data Index: 205411 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0775. Min Act: -0.0001

Data Index: 138940 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0762. Min Act: -0.0001

Data Index: 946225 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0747. Min Act: -0.0001

Data Index: 239790 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0745. Min Act: -0.0001

Data Index: 33458 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0733. Min Act: -0.0001

Data Index: 211414 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0728. Min Act: -0.0001

Data Index: 684232 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0748. Min Act: -0.0001

Data Index: 705759 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0725. Min Act: -0.0001

Data Index: 804951 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0721. Min Act: -0.0001

Data Index: 462601 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0707. Min Act: -0.0001

Data Index: 314552 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0724. Min Act: -0.0001

Data Index: 939688 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1446 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0720. Min Act: -0.0001

Data Index: 113104 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1278055 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0712. Min Act: -0.0001

Data Index: 247838 (C4 (Web Text))

Max Activating Token Index: 734