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

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

Neuron 1863 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4588. Min Range: -1.4588

Max Act: 1.4588. Min Act: -0.0000

Data Index: 47412 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.4588. Min Range: -1.4588

Max Act: 1.2717. Min Act: -0.0000

Data Index: 536507 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.4588. Min Range: -1.4588

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1157978 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 1.4588. Min Range: -1.4588

Max Act: 1.1986. Min Act: -0.0000

Data Index: 284241 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.4588. Min Range: -1.4588

Max Act: 1.0907. Min Act: -0.0000

Data Index: 485024 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.4588. Min Range: -1.4588

Max Act: 1.0389. Min Act: -0.0000

Data Index: 746003 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1020596 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9789. Min Act: -0.0000

Data Index: 494082 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9685. Min Act: -0.0000

Data Index: 464861 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9525. Min Act: -0.0000

Data Index: 461426 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1103314 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9745. Min Act: -0.0000

Data Index: 250093 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9426. Min Act: -0.0000

Data Index: 792008 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9417. Min Act: -0.0000

Data Index: 549919 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9679. Min Act: -0.0000

Data Index: 905522 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9311. Min Act: -0.0000

Data Index: 476919 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1068225 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.8687. Min Act: -0.0000

Data Index: 199512 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.9373. Min Act: -0.0000

Data Index: 427363 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.4588. Min Range: -1.4588

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1086478 (C4 (Web Text))

Max Activating Token Index: 659