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

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

Neuron 3512 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1253172 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1580597 (Python Code)

Max Activating Token Index: 131

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1430578 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1602414 (Python Code)

Max Activating Token Index: 948

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1175380 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1592792 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1489369 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0522. Min Act: -0.0001

Data Index: 231756 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1446721 (Python Code)

Max Activating Token Index: 491

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0523. Min Act: -0.0001

Data Index: 633302 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0516. Min Act: -0.0001

Data Index: 1429009 (Python Code)

Max Activating Token Index: 779

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0467. Min Act: -0.0001

Data Index: 90793 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1353179 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1474962 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1215128 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0459. Min Act: -0.0001

Data Index: 366997 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0472. Min Act: -0.0001

Data Index: 782405 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0463. Min Act: -0.0001

Data Index: 587861 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0443. Min Act: -0.0001

Data Index: 571663 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1453372 (Python Code)

Max Activating Token Index: 819