Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1917 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2682. Min Range: -3.2682

Max Act: 3.2682. Min Act: -0.0000

Data Index: 11435 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 3.2682. Min Range: -3.2682

Max Act: 3.2011. Min Act: -0.0000

Data Index: 159227 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 3.2682. Min Range: -3.2682

Max Act: 3.1388. Min Act: -0.0000

Data Index: 702679 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.7730. Min Act: -0.0000

Data Index: 444371 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.5430. Min Act: -0.0000

Data Index: 915009 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.5890. Min Act: -0.0000

Data Index: 1190886 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.6800. Min Act: -0.0000

Data Index: 1021027 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.7288. Min Act: -0.0000

Data Index: 736884 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.4507. Min Act: -0.0000

Data Index: 1134295 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.4237. Min Act: -0.0000

Data Index: 948342 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.2894. Min Act: -0.0000

Data Index: 399987 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.2590. Min Act: -0.0000

Data Index: 48229 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.3640. Min Act: -0.0000

Data Index: 1162444 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.5067. Min Act: -0.0000

Data Index: 12598 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.3517. Min Act: -0.0000

Data Index: 97770 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.3210. Min Act: -0.0000

Data Index: 851 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.2920. Min Act: -0.0000

Data Index: 46364 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.0834. Min Act: -0.0000

Data Index: 464025 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.1891. Min Act: -0.0000

Data Index: 366895 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 3.2682. Min Range: -3.2682

Max Act: 2.1518. Min Act: -0.0000

Data Index: 1055204 (C4 (Web Text))

Max Activating Token Index: 339