Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5315 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1482. Min Act: -0.0001

Data Index: 189311 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1160. Min Act: -0.0001

Data Index: 542644 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0736. Min Act: -0.0001

Data Index: 813055 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0762. Min Act: -0.0001

Data Index: 928808 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0709. Min Act: -0.0001

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0679. Min Act: -0.0002

Data Index: 999036 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1227195 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1333286 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1162950 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0604. Min Act: -0.0002

Data Index: 328005 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1022446 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0621. Min Act: -0.0001

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0603. Min Act: -0.0001

Data Index: 115609 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0633. Min Act: -0.0002

Data Index: 938149 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0697. Min Act: -0.0002

Data Index: 333601 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0585. Min Act: -0.0001

Data Index: 382016 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0607. Min Act: -0.0002

Data Index: 195380 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0606. Min Act: -0.0002

Data Index: 441531 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0621. Min Act: -0.0002

Data Index: 302956 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0592. Min Act: -0.0002

Data Index: 625466 (C4 (Web Text))

Max Activating Token Index: 85