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

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

Neuron 702 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: 0.0661. Min Range: -0.0661

Max Act: 0.0661. Min Act: -0.0002

Data Index: 118171 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0661. Min Act: -0.0002

Data Index: 5725 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1208419 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0629. Min Act: -0.0002

Data Index: 553650 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0604. Min Act: -0.0002

Data Index: 879252 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1026980 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0589. Min Act: -0.0002

Data Index: 496067 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0588. Min Act: -0.0002

Data Index: 744835 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0603. Min Act: -0.0002

Data Index: 52357 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0584. Min Act: -0.0002

Data Index: 711474 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0559. Min Act: -0.0002

Data Index: 145011 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0576. Min Act: -0.0002

Data Index: 117580 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1259913 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0573. Min Act: -0.0002

Data Index: 471805 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0601. Min Act: -0.0002

Data Index: 667797 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0602. Min Act: -0.0002

Data Index: 218227 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0570. Min Act: -0.0002

Data Index: 651789 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0575. Min Act: -0.0002

Data Index: 668100 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0552. Min Act: -0.0002

Data Index: 948901 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.0661. Min Range: -0.0661

Max Act: 0.0542. Min Act: -0.0002

Data Index: 112370 (C4 (Web Text))

Max Activating Token Index: 434