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

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

Neuron 29 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1722. Min Act: -0.0000

Data Index: 257416 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1366. Min Act: -0.0000

Data Index: 581636 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1365. Min Act: -0.0000

Data Index: 77727 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1352. Min Act: -0.0000

Data Index: 556278 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1193. Min Act: -0.0000

Data Index: 700617 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1045. Min Act: -0.0000

Data Index: 526700 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1081. Min Act: -0.0000

Data Index: 575347 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1018970 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1047. Min Act: -0.0000

Data Index: 867149 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1011. Min Act: -0.0000

Data Index: 450683 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1035712 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1051. Min Act: -0.0000

Data Index: 135285 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0911. Min Act: -0.0000

Data Index: 54869 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0923. Min Act: 0.0000

Data Index: 159735 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0938. Min Act: -0.0000

Data Index: 438906 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0912. Min Act: 0.0000

Data Index: 707184 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1146139 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0834. Min Act: 0.0000

Data Index: 1350224 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0815. Min Act: -0.0000

Data Index: 555117 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0812. Min Act: -0.0000

Data Index: 327243 (C4 (Web Text))

Max Activating Token Index: 722