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

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

Neuron 5156 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.6092. Min Act: -0.0000

Data Index: 1392780 (Python Code)

Max Activating Token Index: 93

Text #1

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.6039. Min Act: -0.0000

Data Index: 1470146 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.4861. Min Act: -0.0000

Data Index: 1440901 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.5075. Min Act: -0.0000

Data Index: 1437719 (Python Code)

Max Activating Token Index: 223

Text #4

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.5029. Min Act: -0.0000

Data Index: 1637980 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1585608 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1112312 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.4957. Min Act: -0.0000

Data Index: 1586860 (Python Code)

Max Activating Token Index: 590

Text #8

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1528183 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1545262 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.1800. Min Act: -0.0000

Data Index: 1503243 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.2876. Min Act: -0.0000

Data Index: 184545 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1478608 (Python Code)

Max Activating Token Index: 588

Text #13

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1512415 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1395108 (Python Code)

Max Activating Token Index: 388

Text #15

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1563951 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.0585. Min Act: -0.0000

Data Index: 1656835 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1598200 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1409864 (Python Code)

Max Activating Token Index: 474

Text #19

Max Range: 1.6092. Min Range: -1.6092

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1470130 (Python Code)

Max Activating Token Index: 43