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

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

Neuron 4378 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: 1.0586. Min Range: -1.0586

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1524354 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 1.0586. Min Range: -1.0586

Max Act: 1.0094. Min Act: -0.0000

Data Index: 1500475 (Python Code)

Max Activating Token Index: 280

Text #2

Max Range: 1.0586. Min Range: -1.0586

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1634629 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1614993 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1628239 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1393203 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1656079 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1575061 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1603653 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1586847 (Python Code)

Max Activating Token Index: 543

Text #10

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.9040. Min Act: -0.0001

Data Index: 1529295 (Python Code)

Max Activating Token Index: 414

Text #11

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1547000 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1510857 (Python Code)

Max Activating Token Index: 619

Text #13

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.7833. Min Act: 0.0000

Data Index: 19177 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1389893 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.6851. Min Act: -0.0000

Data Index: 617311 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1409087 (Python Code)

Max Activating Token Index: 509

Text #17

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.6775. Min Act: 0.0000

Data Index: 232048 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.6449. Min Act: -0.0000

Data Index: 380832 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.6139. Min Act: -0.0000

Data Index: 640409 (C4 (Web Text))

Max Activating Token Index: 592