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

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

Neuron 4778 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1480071 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1606746 (Python Code)

Max Activating Token Index: 99

Text #2

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1389039 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1364232 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1528140 (Python Code)

Max Activating Token Index: 535

Text #5

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1575931 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1570733 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1452435 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1656989 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1184455 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1452611 (Python Code)

Max Activating Token Index: 232

Text #11

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1461315 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1284464 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1507773 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1229901 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1505481 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1410226 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1096191 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1653078 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 0.9335. Min Range: -0.9335

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1440727 (Python Code)

Max Activating Token Index: 185