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

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

Neuron 3697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1508652 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1382460 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1394641 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1501033 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1631834 (Python Code)

Max Activating Token Index: 307

Text #5

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1405302 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1472268 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1497807 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1500197 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1378329 (Python Code)

Max Activating Token Index: 915

Text #10

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1455307 (Python Code)

Max Activating Token Index: 950

Text #11

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1377722 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1369180 (Python Code)

Max Activating Token Index: 667

Text #13

Max Range: 1.6350. Min Range: -1.6350

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1430495 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1452914 (Python Code)

Max Activating Token Index: 551

Text #15

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1498125 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1649780 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1418761 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1608896 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 1.6350. Min Range: -1.6350

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1595112 (Python Code)

Max Activating Token Index: 82