Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 704 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0002

Data Index: 496575 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0503. Min Act: -0.0002

Data Index: 958409 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0484. Min Act: -0.0002

Data Index: 26805 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0485. Min Act: -0.0002

Data Index: 382498 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0480. Min Act: -0.0002

Data Index: 596599 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0434. Min Act: -0.0002

Data Index: 820518 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0464. Min Act: -0.0001

Data Index: 574245 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0445. Min Act: -0.0001

Data Index: 926604 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0458. Min Act: -0.0001

Data Index: 32649 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0441. Min Act: -0.0001

Data Index: 702509 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0530. Min Act: -0.0001

Data Index: 938057 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0446. Min Act: -0.0002

Data Index: 863322 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0445. Min Act: -0.0001

Data Index: 88866 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1099069 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0480. Min Act: -0.0002

Data Index: 445533 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0469. Min Act: -0.0002

Data Index: 838524 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0419. Min Act: -0.0002

Data Index: 107449 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1037350 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0001

Data Index: 374124 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0447. Min Act: -0.0002

Data Index: 735148 (C4 (Web Text))

Max Activating Token Index: 786