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

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

Neuron 2520 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: 2.4744. Min Range: -2.4744

Max Act: 2.4744. Min Act: -0.0000

Data Index: 1484491 (Python Code)

Max Activating Token Index: 524

Text #1

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.0431. Min Act: -0.0000

Data Index: 1510696 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9395. Min Act: -0.0000

Data Index: 1640262 (Python Code)

Max Activating Token Index: 768

Text #3

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9362. Min Act: -0.0000

Data Index: 1559451 (Python Code)

Max Activating Token Index: 635

Text #4

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.8067. Min Act: -0.0000

Data Index: 1481833 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7703. Min Act: -0.0000

Data Index: 1369163 (Python Code)

Max Activating Token Index: 314

Text #6

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9401. Min Act: -0.0000

Data Index: 1381259 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.8111. Min Act: -0.0000

Data Index: 1498857 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1472486 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1448107 (Python Code)

Max Activating Token Index: 653

Text #10

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7475. Min Act: -0.0000

Data Index: 1392580 (Python Code)

Max Activating Token Index: 998

Text #11

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6705. Min Act: -0.0000

Data Index: 1592314 (Python Code)

Max Activating Token Index: 313

Text #12

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1482961 (Python Code)

Max Activating Token Index: 63

Text #13

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.7041. Min Act: -0.0000

Data Index: 1507710 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6947. Min Act: -0.0000

Data Index: 1505322 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1446872 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1456683 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.6058. Min Act: -0.0000

Data Index: 1389555 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1398528 (Python Code)

Max Activating Token Index: 759

Text #19

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1656336 (Python Code)

Max Activating Token Index: 631