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

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

Neuron 3418 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.3044. Min Act: -0.0000

Data Index: 1348419 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1233821 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.1525. Min Act: -0.0000

Data Index: 808367 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 1.3044. Min Range: -1.3044

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1319253 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9936. Min Act: -0.0000

Data Index: 16776 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9798. Min Act: -0.0000

Data Index: 336301 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9381. Min Act: -0.0000

Data Index: 305067 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1017139 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9201. Min Act: -0.0000

Data Index: 506345 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8861. Min Act: -0.0000

Data Index: 120697 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8871. Min Act: -0.0000

Data Index: 825956 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9155. Min Act: -0.0000

Data Index: 445844 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1230487 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8630. Min Act: -0.0000

Data Index: 769654 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9027. Min Act: -0.0000

Data Index: 185635 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9021. Min Act: -0.0000

Data Index: 274677 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.9148. Min Act: -0.0000

Data Index: 650769 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8920. Min Act: -0.0000

Data Index: 231408 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8140. Min Act: -0.0000

Data Index: 762081 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.3044. Min Range: -1.3044

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1100159 (C4 (Web Text))

Max Activating Token Index: 502