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

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

Neuron 5006 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6679. Min Range: -1.6679

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1075032 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.6679. Min Range: -1.6679

Max Act: 1.5267. Min Act: 0.0000

Data Index: 192615 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.6679. Min Range: -1.6679

Max Act: 1.1867. Min Act: -0.0000

Data Index: 274598 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.8444. Min Act: -0.0000

Data Index: 573779 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.8587. Min Act: -0.0000

Data Index: 481208 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.8347. Min Act: 0.0000

Data Index: 927885 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.8275. Min Act: -0.0000

Data Index: 989456 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.8377. Min Act: -0.0000

Data Index: 907151 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.8119. Min Act: -0.0000

Data Index: 617902 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1413457 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7778. Min Act: -0.0000

Data Index: 379775 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7255. Min Act: -0.0000

Data Index: 4391 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1234772 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1300746 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7608. Min Act: -0.0000

Data Index: 720690 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1433291 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7145. Min Act: -0.0000

Data Index: 208049 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1310549 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1338381 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.6679. Min Range: -1.6679

Max Act: 0.7078. Min Act: -0.0000

Data Index: 390748 (C4 (Web Text))

Max Activating Token Index: 557