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

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

Neuron 3478 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: 0.6849. Min Range: -0.6849

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1385386 (Python Code)

Max Activating Token Index: 618

Text #1

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1458655 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1513342 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5752. Min Act: -0.0001

Data Index: 1455985 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6097. Min Act: -0.0001

Data Index: 1419478 (Python Code)

Max Activating Token Index: 1001

Text #5

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1471788 (Python Code)

Max Activating Token Index: 553

Text #6

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1414014 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5286. Min Act: -0.0001

Data Index: 1588186 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1514221 (Python Code)

Max Activating Token Index: 360

Text #9

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1403256 (Python Code)

Max Activating Token Index: 815

Text #10

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1625570 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1413971 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1362523 (Python Code)

Max Activating Token Index: 536

Text #13

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1428778 (Python Code)

Max Activating Token Index: 501

Text #14

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1368474 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1623098 (Python Code)

Max Activating Token Index: 886

Text #16

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1455212 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1602134 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1472296 (Python Code)

Max Activating Token Index: 331

Text #19

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1445013 (Python Code)

Max Activating Token Index: 631