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

Dataset: The Pile

Neuron 1484 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: 4.3495. Min Range: -4.3495

Max Act: 4.3495. Min Act: -0.0000

Data Index: 1412749 (The Pile)

Max Activating Token Index: 330

Text #1

Max Range: 4.3495. Min Range: -4.3495

Max Act: 4.0136. Min Act: -0.0000

Data Index: 1540353 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 4.3495. Min Range: -4.3495

Max Act: 4.0112. Min Act: -0.0000

Data Index: 256132 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.8461. Min Act: -0.0000

Data Index: 931948 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.8931. Min Act: -0.0000

Data Index: 1387492 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.7450. Min Act: -0.0000

Data Index: 1284999 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.7717. Min Act: -0.0000

Data Index: 1088466 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.7393. Min Act: -0.0000

Data Index: 1989635 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.4351. Min Act: -0.0000

Data Index: 1721372 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.5333. Min Act: -0.0000

Data Index: 1682001 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.4854. Min Act: -0.0000

Data Index: 1492623 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.4127. Min Act: -0.0000

Data Index: 1207769 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.8507. Min Act: -0.0000

Data Index: 1157666 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.3373. Min Act: -0.0000

Data Index: 1705411 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.1794. Min Act: -0.0000

Data Index: 39878 (The Pile)

Max Activating Token Index: 933

Text #15

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.1733. Min Act: -0.0000

Data Index: 1781715 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.2635. Min Act: -0.0000

Data Index: 1003220 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.2738. Min Act: -0.0000

Data Index: 1809581 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.5709. Min Act: -0.0001

Data Index: 144638 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 4.3495. Min Range: -4.3495

Max Act: 3.0826. Min Act: -0.0000

Data Index: 638584 (The Pile)

Max Activating Token Index: 608