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

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

Neuron 3600 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: 0.5719. Min Range: -0.5719

Max Act: 0.5719. Min Act: -0.0000

Data Index: 43807 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.5497. Min Act: -0.0000

Data Index: 663531 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1026266 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1143890 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1138990 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4945. Min Act: -0.0000

Data Index: 390486 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1180435 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4752. Min Act: -0.0000

Data Index: 809100 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1234774 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4299. Min Act: -0.0000

Data Index: 430397 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4599. Min Act: -0.0000

Data Index: 287729 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4423. Min Act: -0.0000

Data Index: 338623 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1155116 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4119. Min Act: -0.0000

Data Index: 89214 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4243. Min Act: -0.0000

Data Index: 832783 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1271453 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4476. Min Act: -0.0000

Data Index: 174766 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4320. Min Act: -0.0000

Data Index: 547556 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4127. Min Act: -0.0000

Data Index: 852862 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.5719. Min Range: -0.5719

Max Act: 0.4269. Min Act: -0.0000

Data Index: 451120 (C4 (Web Text))

Max Activating Token Index: 364