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

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

Neuron 1167 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: 4.1551. Min Range: -4.1551

Max Act: 4.1551. Min Act: -0.0000

Data Index: 1493885 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 4.1551. Min Range: -4.1551

Max Act: 4.1454. Min Act: -0.0000

Data Index: 1449119 (Python Code)

Max Activating Token Index: 533

Text #2

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.8766. Min Act: -0.0000

Data Index: 1648552 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.6126. Min Act: -0.0000

Data Index: 1444381 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.5364. Min Act: -0.0000

Data Index: 1367637 (Python Code)

Max Activating Token Index: 225

Text #5

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.3073. Min Act: -0.0000

Data Index: 1612214 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.4264. Min Act: -0.0000

Data Index: 1467016 (Python Code)

Max Activating Token Index: 472

Text #7

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.9098. Min Act: -0.0000

Data Index: 1419700 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.0170. Min Act: -0.0000

Data Index: 1377421 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.1265. Min Act: -0.0000

Data Index: 1374013 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.9503. Min Act: -0.0000

Data Index: 1613345 (Python Code)

Max Activating Token Index: 481

Text #11

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.7969. Min Act: -0.0000

Data Index: 1621988 (Python Code)

Max Activating Token Index: 501

Text #12

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.0235. Min Act: -0.0000

Data Index: 1582890 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 4.1551. Min Range: -4.1551

Max Act: 3.0150. Min Act: -0.0000

Data Index: 1380854 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.4357. Min Act: -0.0000

Data Index: 1408208 (Python Code)

Max Activating Token Index: 849

Text #15

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.8407. Min Act: -0.0000

Data Index: 1533630 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.9478. Min Act: -0.0000

Data Index: 1422251 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.9460. Min Act: -0.0000

Data Index: 1361488 (Python Code)

Max Activating Token Index: 967

Text #18

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.7813. Min Act: -0.0000

Data Index: 1411363 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 4.1551. Min Range: -4.1551

Max Act: 2.6516. Min Act: -0.0000

Data Index: 1493031 (Python Code)

Max Activating Token Index: 978