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

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

Neuron 505 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0751. Min Range: -1.0751

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1648787 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 1.0751. Min Range: -1.0751

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1530721 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1478573 (Python Code)

Max Activating Token Index: 264

Text #3

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1541292 (Python Code)

Max Activating Token Index: 267

Text #4

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1612696 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1478895 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1418344 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1516255 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1597520 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1491087 (Python Code)

Max Activating Token Index: 814

Text #10

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1378365 (Python Code)

Max Activating Token Index: 915

Text #11

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1405912 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1580354 (Python Code)

Max Activating Token Index: 788

Text #13

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1653610 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1408532 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1637122 (Python Code)

Max Activating Token Index: 923

Text #16

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1622609 (Python Code)

Max Activating Token Index: 407

Text #17

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1582031 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1482152 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 1.0751. Min Range: -1.0751

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1434037 (Python Code)

Max Activating Token Index: 450