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

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

Neuron 2975 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.7441. Min Act: -0.0002

Data Index: 850110 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.4357. Min Act: -0.0002

Data Index: 649273 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5393. Min Act: -0.0002

Data Index: 589315 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 3.7441. Min Range: -3.7441

Max Act: 2.8684. Min Act: -0.0002

Data Index: 535065 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2480. Min Act: -0.0002

Data Index: 1271857 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3529. Min Act: -0.0002

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.1961. Min Act: -0.0002

Data Index: 1015860 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 3.7441. Min Range: -3.7441

Max Act: 2.9259. Min Act: -0.0002

Data Index: 662583 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.1720. Min Act: -0.0002

Data Index: 1209612 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.1359. Min Act: -0.0002

Data Index: 1164472 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3996. Min Act: -0.0002

Data Index: 319293 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3639. Min Act: -0.0002

Data Index: 53002 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.0581. Min Act: -0.0002

Data Index: 1336687 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.1937. Min Act: -0.0002

Data Index: 298915 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.0294. Min Act: -0.0002

Data Index: 200238 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3209. Min Act: -0.0002

Data Index: 335719 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2795. Min Act: -0.0002

Data Index: 558907 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2520. Min Act: -0.0002

Data Index: 152264 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2013. Min Act: -0.0002

Data Index: 708154 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 3.7441. Min Range: -3.7441

Max Act: 2.9415. Min Act: -0.0002

Data Index: 220340 (C4 (Web Text))

Max Activating Token Index: 910