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

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

Neuron 3383 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: 0.7708. Min Range: -0.7708

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1464486 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1652739 (Python Code)

Max Activating Token Index: 430

Text #2

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1576409 (Python Code)

Max Activating Token Index: 415

Text #3

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1497942 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1482461 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1496930 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1374216 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1463753 (Python Code)

Max Activating Token Index: 563

Text #8

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1400517 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1403924 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1563194 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1410313 (Python Code)

Max Activating Token Index: 553

Text #12

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1360815 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1593592 (Python Code)

Max Activating Token Index: 289

Text #14

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1360591 (Python Code)

Max Activating Token Index: 551

Text #15

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1497948 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1516609 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1503208 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1596857 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1361334 (Python Code)

Max Activating Token Index: 230