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

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

Neuron 4403 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: 1.5789. Min Range: -1.5789

Max Act: 1.5789. Min Act: -0.0000

Data Index: 1099642 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.5355. Min Act: -0.0000

Data Index: 722364 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.4735. Min Act: -0.0000

Data Index: 639007 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3600. Min Act: -0.0000

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.4305. Min Act: -0.0000

Data Index: 101951 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3857. Min Act: -0.0000

Data Index: 193855 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3400. Min Act: -0.0000

Data Index: 946761 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2858. Min Act: -0.0000

Data Index: 1204611 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3482. Min Act: -0.0000

Data Index: 93186 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1915. Min Act: -0.0000

Data Index: 541275 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2508. Min Act: -0.0000

Data Index: 534991 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1636. Min Act: -0.0000

Data Index: 308058 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1241759 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1700. Min Act: -0.0000

Data Index: 117068 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2272. Min Act: -0.0000

Data Index: 414979 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1202. Min Act: -0.0000

Data Index: 583442 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1100. Min Act: -0.0000

Data Index: 324417 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1772. Min Act: -0.0000

Data Index: 937886 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1111. Min Act: -0.0000

Data Index: 194149 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0450. Min Act: -0.0000

Data Index: 493475 (C4 (Web Text))

Max Activating Token Index: 406