Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.9928. Min Act: -0.0000

Data Index: 1551139 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.4027. Min Act: -0.0000

Data Index: 1647434 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.0928. Min Act: -0.0000

Data Index: 1490793 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.1864. Min Act: -0.0000

Data Index: 1526811 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.2850. Min Act: -0.0000

Data Index: 1545975 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.8174. Min Act: -0.0000

Data Index: 1496953 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.1837. Min Act: -0.0000

Data Index: 1571607 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1458883 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.0889. Min Act: -0.0000

Data Index: 1566761 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.8512. Min Act: -0.0000

Data Index: 1606094 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.8962. Min Act: -0.0000

Data Index: 1430513 (Python Code)

Max Activating Token Index: 759

Text #11

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1540965 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.9147. Min Act: -0.0000

Data Index: 1550237 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.6753. Min Act: -0.0000

Data Index: 1497887 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.7779. Min Act: -0.0000

Data Index: 140323 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1406289 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1641386 (Python Code)

Max Activating Token Index: 857

Text #17

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.7352. Min Act: -0.0000

Data Index: 1466546 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.8301. Min Act: -0.0000

Data Index: 1460682 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 2.9928. Min Range: -2.9928

Max Act: 1.6145. Min Act: -0.0000

Data Index: 1548306 (Python Code)

Max Activating Token Index: 611