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

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

Neuron 4726 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1394802 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1380870 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1624894 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1433133 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1619002 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1479507 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1560202 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1378098 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1421447 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1540185 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1363634 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1645498 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1538694 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1474164 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1640353 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1590863 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1587935 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1418243 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1641719 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.9825. Min Range: -0.9825

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1544808 (Python Code)

Max Activating Token Index: 6