Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1814 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0674. Min Act: -0.0006

Data Index: 848728 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0694. Min Act: -0.0006

Data Index: 226733 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0705. Min Act: -0.0006

Data Index: 833027 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0006

Data Index: 308035 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0675. Min Act: -0.0006

Data Index: 176078 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0664. Min Act: -0.0006

Data Index: 470448 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0660. Min Act: -0.0006

Data Index: 1260732 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0655. Min Act: -0.0006

Data Index: 772027 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0652. Min Act: -0.0006

Data Index: 449824 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0653. Min Act: -0.0006

Data Index: 773527 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0645. Min Act: -0.0006

Data Index: 1000733 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0667. Min Act: -0.0006

Data Index: 418058 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0599. Min Act: -0.0006

Data Index: 1308424 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0664. Min Act: -0.0006

Data Index: 382965 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0657. Min Act: -0.0006

Data Index: 1027307 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0626. Min Act: -0.0006

Data Index: 273801 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0649. Min Act: -0.0006

Data Index: 1026271 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0555. Min Act: -0.0006

Data Index: 830742 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0617. Min Act: -0.0006

Data Index: 676076 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0611. Min Act: -0.0006

Data Index: 1302611 (C4 (Web Text))

Max Activating Token Index: 14