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

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

Neuron 4527 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.6089. Min Act: -0.0000

Data Index: 935222 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.2728. Min Act: -0.0000

Data Index: 781493 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.3264. Min Act: -0.0000

Data Index: 219617 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1768. Min Act: -0.0000

Data Index: 1091755 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1166808 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1283981 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1661. Min Act: -0.0001

Data Index: 1351290 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.0990. Min Act: -0.0000

Data Index: 931931 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1143482 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1308269 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.0797. Min Act: -0.0001

Data Index: 509517 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1572471 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1209810 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1356. Min Act: -0.0000

Data Index: 136469 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.0113. Min Act: -0.0000

Data Index: 333418 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1144804 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.0514. Min Act: -0.0000

Data Index: 1169763 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.6089. Min Range: -1.6089

Max Act: 0.9533. Min Act: -0.0000

Data Index: 152571 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.0311. Min Act: -0.0000

Data Index: 659078 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 1.6089. Min Range: -1.6089

Max Act: 1.1006. Min Act: -0.0000

Data Index: 236795 (C4 (Web Text))

Max Activating Token Index: 503