Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1268 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 1.1267. Min Range: -1.1267

Max Act: 1.1267. Min Act: -0.0006

Data Index: 1449149 (Python Code)

Max Activating Token Index: 711

Text #1

Max Range: 1.1267. Min Range: -1.1267

Max Act: 1.0144. Min Act: -0.0006

Data Index: 1376187 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9859. Min Act: -0.0006

Data Index: 1537289 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 1.1267. Min Range: -1.1267

Max Act: 1.0132. Min Act: -0.0006

Data Index: 1651004 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 1.1267. Min Range: -1.1267

Max Act: 1.0147. Min Act: -0.0006

Data Index: 1638675 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9525. Min Act: -0.0006

Data Index: 1618879 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9993. Min Act: -0.0006

Data Index: 1481069 (Python Code)

Max Activating Token Index: 132

Text #7

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9027. Min Act: -0.0006

Data Index: 1415281 (Python Code)

Max Activating Token Index: 1006

Text #8

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9319. Min Act: -0.0006

Data Index: 1652628 (Python Code)

Max Activating Token Index: 849

Text #9

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9853. Min Act: -0.0006

Data Index: 1397932 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9833. Min Act: -0.0006

Data Index: 1439425 (Python Code)

Max Activating Token Index: 938

Text #11

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9249. Min Act: -0.0006

Data Index: 1374044 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9214. Min Act: -0.0006

Data Index: 1643704 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9360. Min Act: -0.0006

Data Index: 1467668 (Python Code)

Max Activating Token Index: 125

Text #14

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9136. Min Act: -0.0006

Data Index: 1568999 (Python Code)

Max Activating Token Index: 653

Text #15

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.9047. Min Act: -0.0006

Data Index: 1651531 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.8734. Min Act: -0.0006

Data Index: 1503764 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.8212. Min Act: -0.0006

Data Index: 1627492 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.8396. Min Act: -0.0006

Data Index: 1470359 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 1.1267. Min Range: -1.1267

Max Act: 0.8098. Min Act: -0.0006

Data Index: 1568080 (Python Code)

Max Activating Token Index: 475