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

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

Neuron 1912 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: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0002

Data Index: 480666 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1541119 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0835. Min Act: -0.0002

Data Index: 419552 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0800. Min Act: -0.0002

Data Index: 406857 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0816. Min Act: -0.0002

Data Index: 299813 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0807. Min Act: -0.0002

Data Index: 530935 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1320112 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1036868 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0797. Min Act: -0.0002

Data Index: 921401 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0772. Min Act: -0.0002

Data Index: 764169 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0794. Min Act: -0.0002

Data Index: 244835 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1349411 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1585892 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1299935 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1342321 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1094772 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0753. Min Act: -0.0002

Data Index: 129134 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0739. Min Act: -0.0002

Data Index: 366473 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0732. Min Act: -0.0002

Data Index: 66936 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1220920 (C4 (Web Text))

Max Activating Token Index: 59