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

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

Neuron 4333 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: 0.1867. Min Range: -0.1867

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1553319 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1866. Min Act: -0.0000

Data Index: 878603 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1867. Min Act: 0.0000

Data Index: 83679 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1607580 (Python Code)

Max Activating Token Index: 764

Text #4

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1591. Min Act: -0.0000

Data Index: 799593 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1489. Min Act: -0.0000

Data Index: 202164 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1536. Min Act: 0.0001

Data Index: 28546 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1522. Min Act: -0.0000

Data Index: 648269 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1540. Min Act: -0.0000

Data Index: 826885 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1616079 (Python Code)

Max Activating Token Index: 365

Text #10

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1450. Min Act: -0.0000

Data Index: 307041 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1556778 (Python Code)

Max Activating Token Index: 785

Text #12

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1419045 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1377. Min Act: -0.0000

Data Index: 192556 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1234. Min Act: -0.0000

Data Index: 936791 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1277. Min Act: -0.0000

Data Index: 581002 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1255. Min Act: -0.0000

Data Index: 721237 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1475373 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1122. Min Act: -0.0000

Data Index: 951925 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1133. Min Act: -0.0000

Data Index: 308962 (C4 (Web Text))

Max Activating Token Index: 455