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

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

Neuron 3639 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: 1.2321. Min Range: -1.2321

Max Act: 1.2321. Min Act: -0.0000

Data Index: 191487 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9340. Min Act: -0.0000

Data Index: 413471 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.7601. Min Act: -0.0000

Data Index: 969094 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.7572. Min Act: -0.0000

Data Index: 758574 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1217135 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.7214. Min Act: -0.0000

Data Index: 337043 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1123411 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1099989 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6374. Min Act: -0.0000

Data Index: 905000 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6359. Min Act: -0.0000

Data Index: 44617 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6128. Min Act: -0.0000

Data Index: 587117 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6340. Min Act: -0.0000

Data Index: 634737 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6097. Min Act: -0.0000

Data Index: 326709 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.5838. Min Act: -0.0000

Data Index: 124065 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1267505 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1187251 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.5651. Min Act: -0.0000

Data Index: 154206 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.5585. Min Act: -0.0000

Data Index: 216551 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1153430 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.5676. Min Act: -0.0000

Data Index: 101174 (C4 (Web Text))

Max Activating Token Index: 932