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

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

Neuron 2460 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1162540 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0821. Min Act: -0.0001

Data Index: 568696 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0790. Min Act: -0.0001

Data Index: 915896 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0813. Min Act: -0.0001

Data Index: 618068 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0872. Min Act: -0.0001

Data Index: 797593 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0818. Min Act: -0.0001

Data Index: 429754 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0761. Min Act: -0.0001

Data Index: 459946 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1151527 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1142133 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0750. Min Act: -0.0001

Data Index: 105319 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0745. Min Act: -0.0001

Data Index: 475377 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1211905 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1107158 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1237005 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0700. Min Act: -0.0001

Data Index: 358447 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0698. Min Act: -0.0001

Data Index: 937354 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0717. Min Act: -0.0000

Data Index: 406542 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0704. Min Act: -0.0001

Data Index: 377106 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0693. Min Act: -0.0001

Data Index: 313618 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1085258 (C4 (Web Text))

Max Activating Token Index: 497