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

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

Neuron 3674 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1491690 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1572521 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1007. Min Act: -0.0001

Data Index: 71464 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1069. Min Act: -0.0001

Data Index: 198835 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1553516 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1208781 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1595438 (Python Code)

Max Activating Token Index: 667

Text #7

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1536934 (Python Code)

Max Activating Token Index: 983

Text #8

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1392121 (Python Code)

Max Activating Token Index: 292

Text #9

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1570858 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1515330 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1634977 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1361318 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1506098 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1637747 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1488526 (Python Code)

Max Activating Token Index: 271

Text #16

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1535468 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1576609 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0656. Min Act: -0.0001

Data Index: 420041 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1386180 (Python Code)

Max Activating Token Index: 808