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

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

Neuron 3633 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0674. Min Act: -0.0003

Data Index: 212435 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0003

Data Index: 226810 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0643. Min Act: -0.0003

Data Index: 973013 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0666. Min Act: -0.0003

Data Index: 953144 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1188989 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0578. Min Act: -0.0003

Data Index: 561385 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0564. Min Act: -0.0003

Data Index: 210873 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0564. Min Act: -0.0003

Data Index: 699847 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0540. Min Act: -0.0003

Data Index: 260131 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0520. Min Act: -0.0003

Data Index: 54193 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0502. Min Act: -0.0003

Data Index: 594325 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1200165 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0526. Min Act: -0.0003

Data Index: 712096 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0503. Min Act: -0.0003

Data Index: 702618 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0491. Min Act: -0.0003

Data Index: 61240 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0487. Min Act: -0.0003

Data Index: 268088 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0476. Min Act: -0.0003

Data Index: 376971 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1134495 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0488. Min Act: -0.0003

Data Index: 134805 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1089433 (C4 (Web Text))

Max Activating Token Index: 495