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

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

Neuron 3144 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: 0.5907. Min Range: -0.5907

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1633303 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1408463 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1462912 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1435559 (Python Code)

Max Activating Token Index: 643

Text #4

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1587491 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1425959 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1558598 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1647948 (Python Code)

Max Activating Token Index: 58

Text #8

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1576927 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1526397 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1402425 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1490545 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1369424 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1636217 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1641301 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1365873 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1364466 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1543331 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1652362 (Python Code)

Max Activating Token Index: 816

Text #19

Max Range: 0.5907. Min Range: -0.5907

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1634016 (Python Code)

Max Activating Token Index: 172