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

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

Neuron 716 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1370810 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1394049 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1395316 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1362191 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1392359 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1401997 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1387751 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1387412 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1383100 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1381327 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1398808 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1362985 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1379464 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1377770 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1363638 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1373231 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1394256 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1397383 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1372781 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1366731 (Python Code)

Max Activating Token Index: 1