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

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

Neuron 712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1090025 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2126. Min Act: -0.0001

Data Index: 113899 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1997. Min Act: -0.0000

Data Index: 629875 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2069. Min Act: -0.0001

Data Index: 601490 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1328096 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1208533 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1909. Min Act: -0.0001

Data Index: 814557 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1695. Min Act: -0.0001

Data Index: 372393 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1821. Min Act: -0.0001

Data Index: 801579 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1895. Min Act: -0.0001

Data Index: 969620 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1760. Min Act: -0.0001

Data Index: 1213009 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1790. Min Act: -0.0001

Data Index: 440746 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1755. Min Act: -0.0001

Data Index: 728586 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1777. Min Act: -0.0001

Data Index: 103340 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1591. Min Act: -0.0001

Data Index: 138870 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1730. Min Act: -0.0001

Data Index: 540366 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1054117 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1703. Min Act: -0.0001

Data Index: 865384 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1704. Min Act: -0.0001

Data Index: 333055 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1610. Min Act: -0.0001

Data Index: 580825 (C4 (Web Text))

Max Activating Token Index: 792