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

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

Neuron 326 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5831. Min Range: -8.5831

Max Act: 8.5831. Min Act: -0.0001

Data Index: 640559 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 8.5831. Min Range: -8.5831

Max Act: 8.2971. Min Act: -0.0001

Data Index: 923957 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 8.5831. Min Range: -8.5831

Max Act: 8.4000. Min Act: -0.0001

Data Index: 523890 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.4709. Min Act: -0.0001

Data Index: 1193621 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.5156. Min Act: -0.0001

Data Index: 704564 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.5762. Min Act: -0.0001

Data Index: 565166 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.7030. Min Act: -0.0001

Data Index: 1091749 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.3597. Min Act: -0.0001

Data Index: 316777 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.3541. Min Act: -0.0001

Data Index: 245448 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.2424. Min Act: -0.0001

Data Index: 243325 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.3750. Min Act: -0.0001

Data Index: 276323 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.3292. Min Act: -0.0001

Data Index: 1180072 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.2389. Min Act: -0.0001

Data Index: 152147 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.0432. Min Act: -0.0001

Data Index: 254723 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 8.5831. Min Range: -8.5831

Max Act: 6.7986. Min Act: -0.0001

Data Index: 438314 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 8.5831. Min Range: -8.5831

Max Act: 6.9515. Min Act: -0.0001

Data Index: 980841 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.5693. Min Act: -0.0001

Data Index: 614598 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 8.5831. Min Range: -8.5831

Max Act: 6.8904. Min Act: -0.0001

Data Index: 705420 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 8.5831. Min Range: -8.5831

Max Act: 6.8962. Min Act: -0.0001

Data Index: 670572 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 8.5831. Min Range: -8.5831

Max Act: 7.1568. Min Act: -0.0001

Data Index: 1334387 (C4 (Web Text))

Max Activating Token Index: 689