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

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

Neuron 3893 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4832. Min Act: -0.0000

Data Index: 749648 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4598. Min Act: -0.0000

Data Index: 622898 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4338. Min Act: -0.0000

Data Index: 758926 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4233. Min Act: -0.0000

Data Index: 161648 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3964. Min Act: -0.0000

Data Index: 494364 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4193. Min Act: -0.0000

Data Index: 839676 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3753. Min Act: 0.0001

Data Index: 1291281 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3828. Min Act: -0.0000

Data Index: 458584 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1007022 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3760. Min Act: -0.0000

Data Index: 182141 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1259616 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1062887 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3453. Min Act: -0.0000

Data Index: 922735 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3419. Min Act: 0.0001

Data Index: 240305 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3304. Min Act: -0.0000

Data Index: 672682 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1348857 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3367. Min Act: -0.0000

Data Index: 480430 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3421. Min Act: -0.0000

Data Index: 241303 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1338899 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1039096 (C4 (Web Text))

Max Activating Token Index: 607