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

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

Neuron 2 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: 1.4336. Min Range: -1.4336

Max Act: 1.4249. Min Act: -0.0000

Data Index: 1580863 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.4009. Min Act: -0.0000

Data Index: 903730 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1536686 (Python Code)

Max Activating Token Index: 490

Text #3

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1389271 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1556313 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1609381 (Python Code)

Max Activating Token Index: 405

Text #6

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1599153 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1632071 (Python Code)

Max Activating Token Index: 51

Text #8

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1377255 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1589828 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2530. Min Act: -0.0000

Data Index: 454816 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1613629 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1504884 (Python Code)

Max Activating Token Index: 56

Text #13

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1556392 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1591925 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1575384 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1532817 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1627894 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.1486. Min Act: -0.0000

Data Index: 1633092 (Python Code)

Max Activating Token Index: 455

Text #19

Max Range: 1.4336. Min Range: -1.4336

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1423657 (Python Code)

Max Activating Token Index: 814