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

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

Neuron 2657 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1518422 (Python Code)

Max Activating Token Index: 726

Text #1

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1083936 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1613299 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1427501 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1621140 (Python Code)

Max Activating Token Index: 828

Text #5

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1476587 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1388. Min Act: -0.0000

Data Index: 349880 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1447816 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1579767 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1422272 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1521865 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1444059 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1240. Min Act: -0.0000

Data Index: 416232 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1519734 (Python Code)

Max Activating Token Index: 465

Text #14

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1527884 (Python Code)

Max Activating Token Index: 622

Text #15

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1423486 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1457358 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1441273 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1563812 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1435736 (Python Code)

Max Activating Token Index: 861