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

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

Neuron 689 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: 0.6989. Min Range: -0.6989

Max Act: 0.6989. Min Act: -0.0002

Data Index: 1513650 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.6385. Min Act: -0.0002

Data Index: 1568560 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5974. Min Act: -0.0002

Data Index: 1389253 (Python Code)

Max Activating Token Index: 852

Text #3

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.6354. Min Act: -0.0002

Data Index: 1412589 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.6307. Min Act: -0.0002

Data Index: 1613997 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.6160. Min Act: -0.0002

Data Index: 1482911 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.6079. Min Act: -0.0002

Data Index: 1466646 (Python Code)

Max Activating Token Index: 842

Text #7

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5775. Min Act: -0.0002

Data Index: 1441156 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5742. Min Act: -0.0002

Data Index: 1580353 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5554. Min Act: -0.0002

Data Index: 1435359 (Python Code)

Max Activating Token Index: 283

Text #10

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5892. Min Act: -0.0002

Data Index: 1439654 (Python Code)

Max Activating Token Index: 982

Text #11

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.6063. Min Act: -0.0002

Data Index: 1585863 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5483. Min Act: -0.0002

Data Index: 1575285 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5615. Min Act: -0.0002

Data Index: 1560872 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.6029. Min Act: -0.0002

Data Index: 1528969 (Python Code)

Max Activating Token Index: 911

Text #15

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5775. Min Act: -0.0002

Data Index: 1433370 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5400. Min Act: -0.0002

Data Index: 1421166 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5386. Min Act: -0.0002

Data Index: 1478713 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5346. Min Act: -0.0002

Data Index: 1382778 (Python Code)

Max Activating Token Index: 661

Text #19

Max Range: 0.6989. Min Range: -0.6989

Max Act: 0.5729. Min Act: -0.0002

Data Index: 1375249 (Python Code)

Max Activating Token Index: 198