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

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

Neuron 446 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.8453. Min Act: -0.0000

Data Index: 1521984 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.5507. Min Act: -0.0000

Data Index: 1437816 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1636474 (Python Code)

Max Activating Token Index: 689

Text #3

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1648045 (Python Code)

Max Activating Token Index: 609

Text #4

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1377920 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1640680 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1404509 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1360049 (Python Code)

Max Activating Token Index: 412

Text #8

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1492691 (Python Code)

Max Activating Token Index: 235

Text #9

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1486830 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1378311 (Python Code)

Max Activating Token Index: 394

Text #11

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1425029 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1639548 (Python Code)

Max Activating Token Index: 787

Text #13

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1455273 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1506147 (Python Code)

Max Activating Token Index: 321

Text #15

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1605238 (Python Code)

Max Activating Token Index: 444

Text #16

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1393577 (Python Code)

Max Activating Token Index: 864

Text #17

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1518774 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1631271 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 1.8453. Min Range: -1.8453

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1587249 (Python Code)

Max Activating Token Index: 393