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

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

Neuron 4842 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1271940 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0520. Min Act: -0.0002

Data Index: 656025 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0533. Min Act: -0.0002

Data Index: 792476 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0002

Data Index: 106420 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0510. Min Act: -0.0002

Data Index: 182496 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0500. Min Act: -0.0002

Data Index: 638770 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0463. Min Act: -0.0002

Data Index: 518102 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1383915 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0479. Min Act: -0.0002

Data Index: 468058 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0470. Min Act: -0.0002

Data Index: 651180 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0452. Min Act: -0.0002

Data Index: 332584 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1011920 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0451. Min Act: -0.0002

Data Index: 535472 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1101184 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0475. Min Act: -0.0002

Data Index: 677730 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0451. Min Act: -0.0002

Data Index: 347538 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1275341 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0423. Min Act: -0.0002

Data Index: 988184 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0467. Min Act: -0.0002

Data Index: 255788 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0423. Min Act: -0.0002

Data Index: 154162 (C4 (Web Text))

Max Activating Token Index: 706