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

Dataset: The Pile

Neuron 4481 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: 1.9274. Min Range: -1.9274

Max Act: 1.9274. Min Act: -0.0000

Data Index: 656577 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6228. Min Act: -0.0000

Data Index: 654336 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.8593. Min Act: -0.0000

Data Index: 856653 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1264176 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.8288. Min Act: -0.0000

Data Index: 1883384 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1244508 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.8803. Min Act: -0.0000

Data Index: 1333857 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6865. Min Act: -0.0000

Data Index: 1463516 (The Pile)

Max Activating Token Index: 374

Text #8

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1526977 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7413. Min Act: -0.0000

Data Index: 1561695 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.5971. Min Act: -0.0000

Data Index: 615651 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6690. Min Act: -0.0000

Data Index: 1814431 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7691. Min Act: -0.0000

Data Index: 1690061 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6585. Min Act: -0.0000

Data Index: 530592 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6706. Min Act: -0.0000

Data Index: 829485 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6168. Min Act: -0.0000

Data Index: 754489 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1933016 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.5489. Min Act: -0.0000

Data Index: 318102 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6287. Min Act: -0.0000

Data Index: 1068403 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.5379. Min Act: -0.0000

Data Index: 530372 (The Pile)

Max Activating Token Index: 469