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

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

Neuron 4662 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1089234 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0773. Min Act: -0.0000

Data Index: 507904 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1351778 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0663. Min Act: -0.0000

Data Index: 322498 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1325730 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0609. Min Act: -0.0000

Data Index: 253266 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0610. Min Act: -0.0000

Data Index: 182853 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1030199 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0557. Min Act: -0.0000

Data Index: 353916 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0545. Min Act: -0.0000

Data Index: 543196 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0606. Min Act: -0.0000

Data Index: 528920 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0522. Min Act: -0.0000

Data Index: 915606 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0562. Min Act: -0.0000

Data Index: 279439 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0546. Min Act: -0.0000

Data Index: 833323 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0527. Min Act: -0.0000

Data Index: 94952 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0556. Min Act: -0.0000

Data Index: 480286 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1129281 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1164226 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0558. Min Act: -0.0000

Data Index: 900333 (C4 (Web Text))

Max Activating Token Index: 668