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

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

Neuron 4164 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0001

Data Index: 800410 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0669. Min Act: -0.0001

Data Index: 61930 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0656. Min Act: -0.0001

Data Index: 817834 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1516463 (Python Code)

Max Activating Token Index: 743

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0634. Min Act: -0.0001

Data Index: 977025 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1551711 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1295956 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1584588 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0603. Min Act: -0.0001

Data Index: 275060 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1446987 (Python Code)

Max Activating Token Index: 616

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1556656 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1576824 (Python Code)

Max Activating Token Index: 929

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1630124 (Python Code)

Max Activating Token Index: 914

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1497213 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1650353 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1469756 (Python Code)

Max Activating Token Index: 349

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1440313 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0550. Min Act: -0.0001

Data Index: 158116 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1373878 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1510750 (Python Code)

Max Activating Token Index: 581