Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2815 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.2379. Min Act: -0.0001

Data Index: 654791 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.2303. Min Act: -0.0001

Data Index: 1113678 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1177661 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1899. Min Act: -0.0001

Data Index: 685680 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1785. Min Act: -0.0001

Data Index: 378383 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1845. Min Act: -0.0001

Data Index: 622736 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1779. Min Act: -0.0001

Data Index: 518212 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1805. Min Act: -0.0001

Data Index: 21154 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1698. Min Act: -0.0001

Data Index: 548496 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1639. Min Act: -0.0001

Data Index: 675050 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1698. Min Act: -0.0001

Data Index: 416092 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1108876 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1692. Min Act: -0.0001

Data Index: 711318 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1273588 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1641. Min Act: -0.0001

Data Index: 381744 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1723. Min Act: -0.0001

Data Index: 555358 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1579. Min Act: -0.0001

Data Index: 858007 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1565. Min Act: -0.0001

Data Index: 486130 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1547. Min Act: -0.0001

Data Index: 442038 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.2379. Min Range: -0.2379

Max Act: 0.1608. Min Act: -0.0001

Data Index: 470106 (C4 (Web Text))

Max Activating Token Index: 937