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

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

Neuron 5765 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: 0.6856. Min Range: -0.6856

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1235379 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1077615 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6260. Min Act: -0.0000

Data Index: 55853 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6045. Min Act: -0.0000

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1156228 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6170. Min Act: -0.0000

Data Index: 262079 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6130. Min Act: -0.0000

Data Index: 404724 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1446951 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5753. Min Act: -0.0000

Data Index: 985408 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5494. Min Act: -0.0000

Data Index: 926428 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1258664 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6014. Min Act: -0.0000

Data Index: 108579 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5368. Min Act: -0.0000

Data Index: 249355 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5497. Min Act: -0.0000

Data Index: 981682 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1346251 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5387. Min Act: -0.0000

Data Index: 279720 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5667. Min Act: -0.0000

Data Index: 550656 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5518. Min Act: -0.0000

Data Index: 978236 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6099. Min Act: -0.0000

Data Index: 800915 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1154967 (C4 (Web Text))

Max Activating Token Index: 914