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

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

Neuron 1001 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0001

Data Index: 160699 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1195126 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0680. Min Act: -0.0001

Data Index: 786050 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0657. Min Act: -0.0001

Data Index: 482629 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1026590 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0683. Min Act: -0.0001

Data Index: 38834 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0625. Min Act: -0.0001

Data Index: 205121 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0640. Min Act: -0.0001

Data Index: 113216 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0604. Min Act: -0.0001

Data Index: 290260 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1075888 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0595. Min Act: -0.0001

Data Index: 258422 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0631. Min Act: -0.0001

Data Index: 478774 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1111912 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0602. Min Act: -0.0001

Data Index: 357950 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0599. Min Act: -0.0001

Data Index: 758665 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1223250 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0515. Min Act: -0.0001

Data Index: 447936 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0563. Min Act: -0.0001

Data Index: 379789 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0554. Min Act: -0.0001

Data Index: 477048 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1274006 (C4 (Web Text))

Max Activating Token Index: 311