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

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

Neuron 4490 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.3746. Min Act: -0.0000

Data Index: 582294 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1093625 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.1842. Min Act: -0.0000

Data Index: 400685 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.1582. Min Act: -0.0000

Data Index: 965682 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1296449 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0752. Min Act: -0.0000

Data Index: 455971 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0863. Min Act: -0.0000

Data Index: 884979 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.3746. Min Range: -1.3746

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1173721 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1111824 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1325927 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0567. Min Act: -0.0000

Data Index: 252717 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0084. Min Act: -0.0000

Data Index: 810380 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.3746. Min Range: -1.3746

Max Act: 0.9641. Min Act: -0.0000

Data Index: 361557 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0256. Min Act: -0.0000

Data Index: 334779 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 1.3746. Min Range: -1.3746

Max Act: 1.0235. Min Act: -0.0000

Data Index: 283728 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.3746. Min Range: -1.3746

Max Act: 0.9071. Min Act: -0.0000

Data Index: 141392 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 1.3746. Min Range: -1.3746

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1226644 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.3746. Min Range: -1.3746

Max Act: 0.9627. Min Act: -0.0000

Data Index: 518271 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.3746. Min Range: -1.3746

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1155527 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.3746. Min Range: -1.3746

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1013157 (C4 (Web Text))

Max Activating Token Index: 538