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

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

Neuron 2014 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1399364 (Python Code)

Max Activating Token Index: 613

Text #1

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1404621 (Python Code)

Max Activating Token Index: 561

Text #2

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1399213 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1603625 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1645725 (Python Code)

Max Activating Token Index: 967

Text #5

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1412451 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1434902 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1589266 (Python Code)

Max Activating Token Index: 729

Text #8

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1371520 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1459157 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1447536 (Python Code)

Max Activating Token Index: 498

Text #11

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1645603 (Python Code)

Max Activating Token Index: 993

Text #12

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1556401 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1512851 (Python Code)

Max Activating Token Index: 410

Text #14

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1582002 (Python Code)

Max Activating Token Index: 703

Text #15

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1533158 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1569136 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1510181 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1551122 (Python Code)

Max Activating Token Index: 880

Text #19

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1536512 (Python Code)

Max Activating Token Index: 995