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

Dataset: The Pile

Neuron 2605 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: 0.7403. Min Range: -0.7403

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1835363 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1441702 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1890367 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1753654 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.7013. Min Act: -0.0000

Data Index: 76693 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6144. Min Act: -0.0000

Data Index: 228366 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1203941 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6626. Min Act: -0.0000

Data Index: 798670 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5959. Min Act: -0.0000

Data Index: 782983 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1720513 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.6133. Min Act: -0.0000

Data Index: 232237 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5887. Min Act: -0.0000

Data Index: 218790 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5381. Min Act: -0.0000

Data Index: 392887 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5414. Min Act: -0.0000

Data Index: 32711 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1535656 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5720. Min Act: -0.0000

Data Index: 732858 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5535. Min Act: -0.0001

Data Index: 1418756 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1593523 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5300. Min Act: -0.0000

Data Index: 343200 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 0.7403. Min Range: -0.7403

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1737648 (The Pile)

Max Activating Token Index: 111