Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 154 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.5776. Min Act: -0.0000

Data Index: 1569316 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1656800 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1542539 (Python Code)

Max Activating Token Index: 940

Text #3

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1489957 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.2346. Min Act: -0.0000

Data Index: 1527480 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1630005 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1442171 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1503457 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1468525 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1437088 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1546485 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1494329 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1387736 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1431121 (Python Code)

Max Activating Token Index: 1011

Text #14

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1489343 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1638019 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1647640 (Python Code)

Max Activating Token Index: 961

Text #17

Max Range: 1.5776. Min Range: -1.5776

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1524739 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 1.5776. Min Range: -1.5776

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1601832 (Python Code)

Max Activating Token Index: 795

Text #19

Max Range: 1.5776. Min Range: -1.5776

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1608351 (Python Code)

Max Activating Token Index: 34