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

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

Neuron 3482 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: 4.1222. Min Range: -4.1222

Max Act: 4.1222. Min Act: -0.0000

Data Index: 1342342 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.9564. Min Act: -0.0000

Data Index: 816637 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.9024. Min Act: -0.0000

Data Index: 1225072 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.7693. Min Act: -0.0000

Data Index: 682776 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.6136. Min Act: -0.0000

Data Index: 383218 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.5914. Min Act: -0.0000

Data Index: 980069 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.5902. Min Act: -0.0000

Data Index: 585310 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.5769. Min Act: -0.0000

Data Index: 47184 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.1819. Min Act: -0.0000

Data Index: 275253 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.3317. Min Act: -0.0000

Data Index: 181340 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.1103. Min Act: 0.0000

Data Index: 662507 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.1755. Min Act: 0.0000

Data Index: 164862 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 4.1222. Min Range: -4.1222

Max Act: 3.0134. Min Act: -0.0000

Data Index: 918745 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 4.1222. Min Range: -4.1222

Max Act: 2.9849. Min Act: -0.0000

Data Index: 1314626 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 4.1222. Min Range: -4.1222

Max Act: 2.8810. Min Act: -0.0000

Data Index: 778676 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 4.1222. Min Range: -4.1222

Max Act: 2.8913. Min Act: -0.0000

Data Index: 509347 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 4.1222. Min Range: -4.1222

Max Act: 2.7200. Min Act: -0.0000

Data Index: 306284 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 4.1222. Min Range: -4.1222

Max Act: 2.8364. Min Act: -0.0000

Data Index: 161392 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 4.1222. Min Range: -4.1222

Max Act: 2.8419. Min Act: -0.0000

Data Index: 727806 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 4.1222. Min Range: -4.1222

Max Act: 2.8005. Min Act: -0.0000

Data Index: 1169712 (C4 (Web Text))

Max Activating Token Index: 282