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

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

Neuron 250 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1488622 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1480162 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1463217 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1378450 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1379019 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1501666 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1384552 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1494626 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1452126 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1362052 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1373905 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1383895 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1449463 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1448206 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1494503 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1377445 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1378750 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1438781 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1401609 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1389537 (Python Code)

Max Activating Token Index: 1