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

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

Neuron 3586 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: 2.9631. Min Range: -2.9631

Max Act: 2.9631. Min Act: -0.0000

Data Index: 1600814 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 2.9631. Min Range: -2.9631

Max Act: 2.1716. Min Act: -0.0000

Data Index: 1549181 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 2.9631. Min Range: -2.9631

Max Act: 2.3358. Min Act: -0.0001

Data Index: 1458239 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 2.9631. Min Range: -2.9631

Max Act: 2.4567. Min Act: -0.0001

Data Index: 1630619 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.9750. Min Act: -0.0001

Data Index: 1410691 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 2.9631. Min Range: -2.9631

Max Act: 2.0394. Min Act: -0.0000

Data Index: 1607925 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.9526. Min Act: -0.0000

Data Index: 1387107 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.9650. Min Act: -0.0001

Data Index: 1627616 (Python Code)

Max Activating Token Index: 924

Text #8

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.9621. Min Act: -0.0001

Data Index: 1534407 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.7204. Min Act: -0.0001

Data Index: 1563539 (Python Code)

Max Activating Token Index: 269

Text #10

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.9806. Min Act: -0.0000

Data Index: 1392761 (Python Code)

Max Activating Token Index: 225

Text #11

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.8553. Min Act: -0.0001

Data Index: 1380664 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.6466. Min Act: -0.0000

Data Index: 1544257 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 2.9631. Min Range: -2.9631

Max Act: 2.1826. Min Act: -0.0000

Data Index: 1404305 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.7746. Min Act: -0.0000

Data Index: 1375532 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1368785 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1446767 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1377836 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.6594. Min Act: -0.0001

Data Index: 1430397 (Python Code)

Max Activating Token Index: 979

Text #19

Max Range: 2.9631. Min Range: -2.9631

Max Act: 1.5215. Min Act: -0.0001

Data Index: 1613466 (Python Code)

Max Activating Token Index: 654