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

Dataset: The Pile

Neuron 1005 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: 3.3640. Min Range: -3.3640

Max Act: 3.0053. Min Act: -0.0000

Data Index: 1776200 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 3.3640. Min Range: -3.3640

Max Act: 3.3640. Min Act: -0.0000

Data Index: 1458217 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 3.3640. Min Range: -3.3640

Max Act: 3.1664. Min Act: -0.0000

Data Index: 536664 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 3.3640. Min Range: -3.3640

Max Act: 3.0617. Min Act: -0.0000

Data Index: 1759559 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.9544. Min Act: -0.0000

Data Index: 906895 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.8814. Min Act: -0.0000

Data Index: 1348340 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 3.3640. Min Range: -3.3640

Max Act: 1.8503. Min Act: -0.0000

Data Index: 742724 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.8250. Min Act: -0.0000

Data Index: 163755 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.8209. Min Act: -0.0000

Data Index: 39063 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.6701. Min Act: -0.0000

Data Index: 283593 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 3.3640. Min Range: -3.3640

Max Act: 3.0292. Min Act: -0.0000

Data Index: 1412540 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.4961. Min Act: -0.0000

Data Index: 916526 (The Pile)

Max Activating Token Index: 752

Text #12

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.4794. Min Act: -0.0000

Data Index: 1855886 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.6077. Min Act: -0.0000

Data Index: 200477 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.5780. Min Act: -0.0000

Data Index: 708687 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.6571. Min Act: -0.0000

Data Index: 122961 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.7460. Min Act: -0.0000

Data Index: 769307 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.3659. Min Act: -0.0000

Data Index: 1476030 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.4721. Min Act: -0.0000

Data Index: 610955 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 3.3640. Min Range: -3.3640

Max Act: 2.5820. Min Act: -0.0000

Data Index: 1800201 (The Pile)

Max Activating Token Index: 435