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

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

Neuron 1359 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: 2.7686. Min Range: -2.7686

Max Act: 2.7686. Min Act: -0.0000

Data Index: 1590808 (Python Code)

Max Activating Token Index: 767

Text #1

Max Range: 2.7686. Min Range: -2.7686

Max Act: 2.0359. Min Act: -0.0000

Data Index: 1544914 (Python Code)

Max Activating Token Index: 781

Text #2

Max Range: 2.7686. Min Range: -2.7686

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1528647 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.8178. Min Act: -0.0000

Data Index: 1437753 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.9973. Min Act: -0.0000

Data Index: 1583007 (Python Code)

Max Activating Token Index: 580

Text #5

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.7394. Min Act: -0.0000

Data Index: 1478125 (Python Code)

Max Activating Token Index: 846

Text #6

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.8095. Min Act: -0.0000

Data Index: 1499796 (Python Code)

Max Activating Token Index: 862

Text #7

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.8350. Min Act: -0.0000

Data Index: 552165 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.8255. Min Act: -0.0000

Data Index: 1523959 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1457214 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.4335. Min Act: -0.0000

Data Index: 608804 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1397161 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1591214 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1368907 (Python Code)

Max Activating Token Index: 526

Text #14

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.5955. Min Act: -0.0000

Data Index: 1636288 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1602850 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.6509. Min Act: -0.0000

Data Index: 1634826 (Python Code)

Max Activating Token Index: 848

Text #17

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1383494 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1362128 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 2.7686. Min Range: -2.7686

Max Act: 1.5197. Min Act: -0.0000

Data Index: 1455643 (Python Code)

Max Activating Token Index: 822