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

Dataset: The Pile

Neuron 4163 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2746. Min Act: -0.0000

Data Index: 562692 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.4122. Min Act: -0.0000

Data Index: 615864 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2982. Min Act: -0.0000

Data Index: 1352423 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.1457. Min Act: -0.0000

Data Index: 664123 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2483. Min Act: -0.0000

Data Index: 1678696 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.1416. Min Act: -0.0000

Data Index: 1055462 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1913001 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1123068 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1787425 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.1220. Min Act: -0.0000

Data Index: 178916 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1906497 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1512167 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1000388 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0161. Min Act: -0.0000

Data Index: 22145 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2102. Min Act: -0.0000

Data Index: 454160 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0878. Min Act: -0.0000

Data Index: 401920 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1733910 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.9685. Min Act: -0.0000

Data Index: 704874 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0480. Min Act: -0.0000

Data Index: 757164 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1101052 (The Pile)

Max Activating Token Index: 611