Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1672 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1143973 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0555. Min Act: -0.0003

Data Index: 463217 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1023386 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0543. Min Act: -0.0003

Data Index: 371885 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0533. Min Act: -0.0003

Data Index: 401146 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1221364 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0520. Min Act: -0.0003

Data Index: 616701 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0501. Min Act: -0.0003

Data Index: 16026 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0485. Min Act: -0.0003

Data Index: 880849 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0499. Min Act: -0.0003

Data Index: 115758 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0502. Min Act: -0.0004

Data Index: 704885 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1196762 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0487. Min Act: -0.0003

Data Index: 243302 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0498. Min Act: -0.0004

Data Index: 1153842 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0484. Min Act: -0.0003

Data Index: 739186 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0509. Min Act: -0.0003

Data Index: 659328 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0485. Min Act: -0.0004

Data Index: 1058323 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0491. Min Act: -0.0003

Data Index: 913307 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0490. Min Act: -0.0003

Data Index: 713129 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1237404 (C4 (Web Text))

Max Activating Token Index: 565