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

Dataset: The Pile

Neuron 1521 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.9810. Min Act: -0.0000

Data Index: 645623 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.8336. Min Act: -0.0000

Data Index: 233677 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.8082. Min Act: -0.0000

Data Index: 1596478 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.4118. Min Act: -0.0000

Data Index: 1102362 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.6090. Min Act: -0.0000

Data Index: 292675 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.2147. Min Act: -0.0000

Data Index: 1781827 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.2550. Min Act: -0.0000

Data Index: 1488792 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.0648. Min Act: -0.0000

Data Index: 961484 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.2587. Min Act: -0.0000

Data Index: 1563923 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.0762. Min Act: -0.0000

Data Index: 589332 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.3616. Min Act: -0.0000

Data Index: 542016 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.1774. Min Act: -0.0000

Data Index: 1888574 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 5.9810. Min Range: -5.9810

Max Act: 4.9596. Min Act: -0.0000

Data Index: 461818 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.1006. Min Act: -0.0000

Data Index: 1076231 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.2118. Min Act: -0.0000

Data Index: 1808898 (The Pile)

Max Activating Token Index: 619

Text #15

Max Range: 5.9810. Min Range: -5.9810

Max Act: 4.9866. Min Act: -0.0000

Data Index: 1469065 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.1464. Min Act: -0.0000

Data Index: 1513739 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.0847. Min Act: -0.0000

Data Index: 433300 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 5.9810. Min Range: -5.9810

Max Act: 4.8263. Min Act: -0.0000

Data Index: 1596425 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 5.9810. Min Range: -5.9810

Max Act: 5.1926. Min Act: -0.0000

Data Index: 1554756 (The Pile)

Max Activating Token Index: 679