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

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

Neuron 1300 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1644585 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.2002. Min Act: -0.0000

Data Index: 880523 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1630. Min Act: -0.0000

Data Index: 246192 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1819. Min Act: -0.0000

Data Index: 845373 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.2519. Min Act: -0.0000

Data Index: 817447 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1512129 (Python Code)

Max Activating Token Index: 753

Text #6

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1540. Min Act: -0.0000

Data Index: 179494 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1039. Min Act: -0.0000

Data Index: 46248 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0663. Min Act: -0.0000

Data Index: 463461 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0622. Min Act: -0.0000

Data Index: 1007202 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1272. Min Act: -0.0000

Data Index: 487503 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1320. Min Act: -0.0000

Data Index: 375659 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.1361. Min Act: -0.0000

Data Index: 602434 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1405163 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0826. Min Act: -0.0000

Data Index: 674964 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.4256. Min Range: -1.4256

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1302262 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0470. Min Act: -0.0000

Data Index: 427208 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0468. Min Act: -0.0000

Data Index: 310131 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0383. Min Act: -0.0000

Data Index: 391533 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.4256. Min Range: -1.4256

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1502186 (Python Code)

Max Activating Token Index: 720