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

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

Neuron 5345 in Layer 1

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: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0002

Data Index: 36621 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1356207 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0832. Min Act: -0.0002

Data Index: 991975 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0817. Min Act: -0.0002

Data Index: 294047 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1042401 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0806. Min Act: -0.0002

Data Index: 973443 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0788. Min Act: -0.0002

Data Index: 950078 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0781. Min Act: -0.0002

Data Index: 535933 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0767. Min Act: -0.0002

Data Index: 116621 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0774. Min Act: -0.0002

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0752. Min Act: -0.0002

Data Index: 979747 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1352707 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0764. Min Act: -0.0002

Data Index: 384472 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1107503 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0764. Min Act: -0.0002

Data Index: 132404 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1116572 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0766. Min Act: -0.0002

Data Index: 865714 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0747. Min Act: -0.0002

Data Index: 975987 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0765. Min Act: -0.0002

Data Index: 388767 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0758. Min Act: -0.0002

Data Index: 964411 (C4 (Web Text))

Max Activating Token Index: 543