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

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

Neuron 2523 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.8546. Min Act: -0.0003

Data Index: 535118 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7531. Min Act: -0.0003

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7717. Min Act: -0.0003

Data Index: 823391 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7551. Min Act: -0.0003

Data Index: 532218 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.7325. Min Act: -0.0003

Data Index: 1268882 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.6513. Min Act: -0.0003

Data Index: 664807 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5946. Min Act: -0.0003

Data Index: 786569 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5610. Min Act: -0.0003

Data Index: 823200 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5360. Min Act: -0.0003

Data Index: 1234021 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5504. Min Act: -0.0003

Data Index: 1196568 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5648. Min Act: -0.0003

Data Index: 1314946 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5431. Min Act: -0.0003

Data Index: 967531 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5451. Min Act: -0.0003

Data Index: 1259530 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5352. Min Act: -0.0003

Data Index: 1217749 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5445. Min Act: -0.0003

Data Index: 727724 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5062. Min Act: -0.0003

Data Index: 1021858 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.4801. Min Act: -0.0003

Data Index: 840366 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.4637. Min Act: -0.0003

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5020. Min Act: -0.0003

Data Index: 169850 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.8546. Min Range: -0.8546

Max Act: 0.5288. Min Act: -0.0003

Data Index: 409974 (C4 (Web Text))

Max Activating Token Index: 191