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

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

Neuron 2287 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8878. Min Range: -4.8878

Max Act: 4.8878. Min Act: -0.0000

Data Index: 1134323 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 4.8878. Min Range: -4.8878

Max Act: 4.7369. Min Act: -0.0000

Data Index: 300314 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 4.8878. Min Range: -4.8878

Max Act: 4.6906. Min Act: -0.0000

Data Index: 1029501 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 4.8878. Min Range: -4.8878

Max Act: 4.1285. Min Act: -0.0000

Data Index: 1133884 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.7390. Min Act: -0.0000

Data Index: 299879 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.8913. Min Act: -0.0000

Data Index: 162362 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 4.8878. Min Range: -4.8878

Max Act: 4.2909. Min Act: -0.0000

Data Index: 205968 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.8481. Min Act: -0.0000

Data Index: 454847 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.3839. Min Act: -0.0000

Data Index: 942244 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.4279. Min Act: -0.0000

Data Index: 589232 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 4.8878. Min Range: -4.8878

Max Act: 2.7209. Min Act: -0.0000

Data Index: 473595 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.1645. Min Act: -0.0000

Data Index: 512917 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.2438. Min Act: -0.0000

Data Index: 1117413 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 4.8878. Min Range: -4.8878

Max Act: 2.9695. Min Act: -0.0000

Data Index: 849659 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 4.8878. Min Range: -4.8878

Max Act: 2.8501. Min Act: -0.0000

Data Index: 1295142 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.3061. Min Act: -0.0000

Data Index: 1201169 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 4.8878. Min Range: -4.8878

Max Act: 2.8592. Min Act: -0.0000

Data Index: 351286 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.1278. Min Act: -0.0000

Data Index: 384138 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 4.8878. Min Range: -4.8878

Max Act: 2.9015. Min Act: -0.0000

Data Index: 872934 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 4.8878. Min Range: -4.8878

Max Act: 3.1275. Min Act: -0.0000

Data Index: 747321 (C4 (Web Text))

Max Activating Token Index: 960