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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.5889. Min Act: -0.0000

Data Index: 382733 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.4901. Min Act: -0.0000

Data Index: 1317892 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.3570. Min Act: -0.0000

Data Index: 212813 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.4623. Min Act: -0.0000

Data Index: 664922 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.4428. Min Act: -0.0000

Data Index: 338942 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.3462. Min Act: -0.0000

Data Index: 183346 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.2773. Min Act: -0.0000

Data Index: 138224 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.0546. Min Act: -0.0000

Data Index: 165495 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9202. Min Act: 0.0000

Data Index: 749422 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9353. Min Act: -0.0000

Data Index: 664833 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.0978. Min Act: -0.0000

Data Index: 507552 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.0867. Min Act: -0.0000

Data Index: 1317485 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.8722. Min Act: -0.0000

Data Index: 836368 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9704. Min Act: -0.0000

Data Index: 1350472 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9346. Min Act: -0.0000

Data Index: 1098019 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.0254. Min Act: -0.0000

Data Index: 478694 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 2.5889. Min Range: -2.5889

Max Act: 2.1363. Min Act: -0.0000

Data Index: 490921 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9190. Min Act: -0.0000

Data Index: 497487 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.8106. Min Act: -0.0000

Data Index: 26205 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 2.5889. Min Range: -2.5889

Max Act: 1.9385. Min Act: -0.0000

Data Index: 1135870 (C4 (Web Text))

Max Activating Token Index: 948