Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 842 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.1004. Min Act: -0.0003

Data Index: 1493393 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0832. Min Act: -0.0003

Data Index: 1594933 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1501459 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1637928 (Python Code)

Max Activating Token Index: 737

Text #4

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1646566 (Python Code)

Max Activating Token Index: 322

Text #5

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1501912 (Python Code)

Max Activating Token Index: 285

Text #6

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1490242 (Python Code)

Max Activating Token Index: 282

Text #7

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1427938 (Python Code)

Max Activating Token Index: 334

Text #8

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1396247 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1483182 (Python Code)

Max Activating Token Index: 778

Text #10

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1397565 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1651910 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1376287 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0684. Min Act: -0.0004

Data Index: 1386387 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1617476 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1436060 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1627579 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1489733 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1396971 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1462262 (Python Code)

Max Activating Token Index: 243