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

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

Neuron 2877 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: 1.0800. Min Range: -1.0800

Max Act: 1.0800. Min Act: -0.0000

Data Index: 611193 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1083573 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0000. Min Act: -0.0000

Data Index: 446312 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1204011 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0053. Min Act: -0.0000

Data Index: 10979 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9512. Min Act: -0.0000

Data Index: 593891 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9415. Min Act: -0.0000

Data Index: 464585 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9338. Min Act: -0.0000

Data Index: 741266 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1172659 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9250. Min Act: -0.0000

Data Index: 455383 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1283109 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8974. Min Act: -0.0000

Data Index: 871186 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8255. Min Act: -0.0000

Data Index: 391616 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1007254 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8687. Min Act: -0.0000

Data Index: 537793 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9115. Min Act: -0.0000

Data Index: 230554 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8511. Min Act: 0.0000

Data Index: 1043073 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8465. Min Act: -0.0000

Data Index: 396937 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8485. Min Act: -0.0000

Data Index: 937739 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.7840. Min Act: -0.0000

Data Index: 215601 (C4 (Web Text))

Max Activating Token Index: 498