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

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

Neuron 2812 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: 1.3896. Min Range: -1.3896

Max Act: 1.2962. Min Act: -0.0000

Data Index: 16536 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2769. Min Act: -0.0000

Data Index: 429302 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3896. Min Act: -0.0000

Data Index: 430185 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1252307 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1091325 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1390005 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1366642 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1839. Min Act: -0.0000

Data Index: 543236 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1414913 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1398. Min Act: -0.0000

Data Index: 41514 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0613. Min Act: -0.0000

Data Index: 922029 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1570230 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1509633 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1271527 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1056129 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1628344 (Python Code)

Max Activating Token Index: 806

Text #16

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1643062 (Python Code)

Max Activating Token Index: 753

Text #17

Max Range: 1.3896. Min Range: -1.3896

Max Act: 0.9661. Min Act: -0.0000

Data Index: 694176 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1147378 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1565911 (Python Code)

Max Activating Token Index: 17