Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5317 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3712. Min Range: -1.3712

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1440534 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 1.3712. Min Range: -1.3712

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1606663 (Python Code)

Max Activating Token Index: 427

Text #2

Max Range: 1.3712. Min Range: -1.3712

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1370830 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1636505 (Python Code)

Max Activating Token Index: 361

Text #4

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1442790 (Python Code)

Max Activating Token Index: 644

Text #5

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1418458 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 1.3712. Min Range: -1.3712

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1463568 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1458115 (Python Code)

Max Activating Token Index: 439

Text #8

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1410336 (Python Code)

Max Activating Token Index: 696

Text #9

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1485915 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1513762 (Python Code)

Max Activating Token Index: 868

Text #11

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1520839 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1592119 (Python Code)

Max Activating Token Index: 974

Text #13

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1609086 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1363580 (Python Code)

Max Activating Token Index: 668

Text #15

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1541342 (Python Code)

Max Activating Token Index: 253

Text #16

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1626604 (Python Code)

Max Activating Token Index: 533

Text #17

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1633893 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1570939 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 1.3712. Min Range: -1.3712

Max Act: 0.7982. Min Act: -0.0000

Data Index: 286307 (C4 (Web Text))

Max Activating Token Index: 316