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

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

Neuron 4700 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: 0.2825. Min Range: -0.2825

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1530729 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1625740 (Python Code)

Max Activating Token Index: 320

Text #2

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1374059 (Python Code)

Max Activating Token Index: 174

Text #3

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1557439 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1510898 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1615865 (Python Code)

Max Activating Token Index: 96

Text #6

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1487484 (Python Code)

Max Activating Token Index: 855

Text #7

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1378131 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1371967 (Python Code)

Max Activating Token Index: 668

Text #9

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1612070 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1453562 (Python Code)

Max Activating Token Index: 94

Text #11

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1376801 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1512205 (Python Code)

Max Activating Token Index: 786

Text #13

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1552757 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1604011 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1530259 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1391995 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1568348 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1556223 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 0.2825. Min Range: -0.2825

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1598471 (Python Code)

Max Activating Token Index: 104