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

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

Neuron 1659 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0002

Data Index: 146812 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1008218 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0539. Min Act: -0.0002

Data Index: 414614 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0590. Min Act: -0.0002

Data Index: 447922 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0585. Min Act: -0.0002

Data Index: 561024 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0612. Min Act: -0.0002

Data Index: 156734 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1206489 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0588. Min Act: -0.0002

Data Index: 34212 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0501. Min Act: -0.0002

Data Index: 458964 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0573. Min Act: -0.0002

Data Index: 274741 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0555. Min Act: -0.0002

Data Index: 798823 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1064567 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0558. Min Act: -0.0002

Data Index: 806812 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0508. Min Act: -0.0002

Data Index: 27861 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0555. Min Act: -0.0002

Data Index: 299926 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0520. Min Act: -0.0002

Data Index: 244728 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0512. Min Act: -0.0002

Data Index: 729743 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0545. Min Act: -0.0002

Data Index: 974634 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1273434 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0529. Min Act: -0.0002

Data Index: 649415 (C4 (Web Text))

Max Activating Token Index: 594