Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3393 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1225. Min Act: -0.0001

Data Index: 1598038 (Python Code)

Max Activating Token Index: 534

Text #1

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.9283. Min Act: -0.0001

Data Index: 1380121 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 1.1331. Min Range: -1.1331

Max Act: 1.1331. Min Act: -0.0001

Data Index: 1567716 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.9923. Min Act: -0.0001

Data Index: 1509690 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.9782. Min Act: -0.0001

Data Index: 1569901 (Python Code)

Max Activating Token Index: 554

Text #5

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.9102. Min Act: -0.0001

Data Index: 1582324 (Python Code)

Max Activating Token Index: 494

Text #6

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8925. Min Act: -0.0001

Data Index: 1368391 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8643. Min Act: -0.0001

Data Index: 1393291 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.9321. Min Act: -0.0001

Data Index: 1507546 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8924. Min Act: -0.0001

Data Index: 1505872 (Python Code)

Max Activating Token Index: 800

Text #10

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8259. Min Act: -0.0001

Data Index: 1554973 (Python Code)

Max Activating Token Index: 274

Text #11

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8139. Min Act: -0.0001

Data Index: 1626595 (Python Code)

Max Activating Token Index: 899

Text #12

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8656. Min Act: -0.0001

Data Index: 1405680 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.7844. Min Act: -0.0001

Data Index: 1460215 (Python Code)

Max Activating Token Index: 383

Text #14

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8266. Min Act: -0.0001

Data Index: 1449682 (Python Code)

Max Activating Token Index: 572

Text #15

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8500. Min Act: -0.0001

Data Index: 1505911 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1618688 (Python Code)

Max Activating Token Index: 901

Text #17

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8202. Min Act: -0.0001

Data Index: 1610558 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8007. Min Act: -0.0001

Data Index: 1403646 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 1.1331. Min Range: -1.1331

Max Act: 0.8446. Min Act: -0.0001

Data Index: 1400605 (Python Code)

Max Activating Token Index: 779