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

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

Neuron 3570 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.4600. Min Act: -0.0000

Data Index: 1619350 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.5244. Min Act: -0.0000

Data Index: 1504985 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.8170. Min Act: -0.0000

Data Index: 1588797 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.7482. Min Act: -0.0000

Data Index: 1417710 (Python Code)

Max Activating Token Index: 1008

Text #4

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6515. Min Act: -0.0000

Data Index: 1578440 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.4828. Min Act: -0.0000

Data Index: 1384540 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.3103. Min Act: -0.0000

Data Index: 1368843 (Python Code)

Max Activating Token Index: 732

Text #7

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.5196. Min Act: -0.0000

Data Index: 1645076 (Python Code)

Max Activating Token Index: 400

Text #8

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.5156. Min Act: -0.0000

Data Index: 1492422 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.2191. Min Act: -0.0000

Data Index: 1579595 (Python Code)

Max Activating Token Index: 351

Text #10

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.3424. Min Act: -0.0000

Data Index: 1511160 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.6137. Min Act: -0.0000

Data Index: 1366751 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.2124. Min Act: -0.0000

Data Index: 1620130 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.3045. Min Act: -0.0000

Data Index: 1520252 (Python Code)

Max Activating Token Index: 561

Text #14

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.4229. Min Act: -0.0000

Data Index: 1402490 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.2721. Min Act: -0.0000

Data Index: 1651145 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.5144. Min Act: -0.0000

Data Index: 1554504 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.5018. Min Act: -0.0000

Data Index: 1609426 (Python Code)

Max Activating Token Index: 590

Text #18

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1526256 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 2.8170. Min Range: -2.8170

Max Act: 2.3243. Min Act: -0.0000

Data Index: 1628920 (Python Code)

Max Activating Token Index: 90