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

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

Neuron 4712 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1783. Min Act: -0.0001

Data Index: 1591925 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1643924 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1451725 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1537266 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1632714 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1376310 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1549437 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1646977 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1646076 (Python Code)

Max Activating Token Index: 436

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1383739 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1582266 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1409588 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1540224 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1555128 (Python Code)

Max Activating Token Index: 959

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1506430 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1596976 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1391489 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1544630 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1595936 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1455934 (Python Code)

Max Activating Token Index: 888