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

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

Neuron 2195 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.5794. Min Act: -0.0000

Data Index: 396410 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1533411 (Python Code)

Max Activating Token Index: 827

Text #2

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.4906. Min Act: -0.0000

Data Index: 1118929 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.3822. Min Act: -0.0000

Data Index: 830839 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.3783. Min Act: 0.0001

Data Index: 1499595 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.2893. Min Act: -0.0000

Data Index: 141670 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.1763. Min Act: -0.0000

Data Index: 509862 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.4051. Min Act: -0.0000

Data Index: 415482 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1441716 (Python Code)

Max Activating Token Index: 649

Text #9

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.3063. Min Act: -0.0000

Data Index: 694493 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1345292 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1363915 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1107966 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.1921. Min Act: -0.0000

Data Index: 367250 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1639255 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.2719. Min Act: -0.0000

Data Index: 118445 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1479207 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1543563 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.2646. Min Act: -0.0000

Data Index: 1258134 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.5794. Min Range: -1.5794

Max Act: 1.1760. Min Act: -0.0000

Data Index: 326472 (C4 (Web Text))

Max Activating Token Index: 766