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

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

Neuron 64 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.1804. Min Act: -0.0000

Data Index: 1654312 (Python Code)

Max Activating Token Index: 839

Text #1

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.0622. Min Act: -0.0000

Data Index: 1604791 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9896. Min Act: -0.0000

Data Index: 1515061 (Python Code)

Max Activating Token Index: 815

Text #3

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.0328. Min Act: -0.0000

Data Index: 1506272 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.0225. Min Act: -0.0000

Data Index: 1416185 (Python Code)

Max Activating Token Index: 651

Text #5

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.0028. Min Act: -0.0000

Data Index: 1533776 (Python Code)

Max Activating Token Index: 567

Text #6

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.1246. Min Act: -0.0001

Data Index: 1483423 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9501. Min Act: -0.0000

Data Index: 1621936 (Python Code)

Max Activating Token Index: 290

Text #8

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.0521. Min Act: -0.0000

Data Index: 1576573 (Python Code)

Max Activating Token Index: 930

Text #9

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9666. Min Act: -0.0000

Data Index: 1499466 (Python Code)

Max Activating Token Index: 713

Text #10

Max Range: 2.1804. Min Range: -2.1804

Max Act: 2.0387. Min Act: -0.0000

Data Index: 1422204 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9292. Min Act: -0.0000

Data Index: 1602127 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9035. Min Act: -0.0000

Data Index: 1395422 (Python Code)

Max Activating Token Index: 851

Text #13

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9557. Min Act: -0.0000

Data Index: 1414877 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9184. Min Act: -0.0000

Data Index: 1561782 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9439. Min Act: -0.0000

Data Index: 1462614 (Python Code)

Max Activating Token Index: 430

Text #16

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.9610. Min Act: -0.0000

Data Index: 1574510 (Python Code)

Max Activating Token Index: 911

Text #17

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.7560. Min Act: -0.0000

Data Index: 1628160 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1554444 (Python Code)

Max Activating Token Index: 759

Text #19

Max Range: 2.1804. Min Range: -2.1804

Max Act: 1.7436. Min Act: -0.0001

Data Index: 1621966 (Python Code)

Max Activating Token Index: 649