Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4440 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.8729. Min Act: -0.0000

Data Index: 371679 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.6268. Min Act: -0.0000

Data Index: 1120375 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.5352. Min Act: -0.0000

Data Index: 902733 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.8729. Min Range: -1.8729

Max Act: 1.1391. Min Act: -0.0000

Data Index: 578011 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.9649. Min Act: -0.0000

Data Index: 280768 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.9667. Min Act: -0.0000

Data Index: 14126 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1172934 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.8387. Min Act: -0.0000

Data Index: 427988 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.8705. Min Act: -0.0000

Data Index: 864215 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.7518. Min Act: -0.0000

Data Index: 792566 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.8212. Min Act: 0.0000

Data Index: 744231 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.8466. Min Act: -0.0000

Data Index: 270826 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.7790. Min Act: -0.0000

Data Index: 502520 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.7937. Min Act: -0.0001

Data Index: 697837 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.8081. Min Act: -0.0000

Data Index: 833859 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.7747. Min Act: 0.0000

Data Index: 761428 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.7746. Min Act: -0.0000

Data Index: 97859 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.7824. Min Act: -0.0000

Data Index: 833504 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.8729. Min Range: -1.8729

Max Act: 0.7793. Min Act: 0.0000

Data Index: 197401 (C4 (Web Text))

Max Activating Token Index: 170