Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 718 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1567793 (Python Code)

Max Activating Token Index: 425

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1447662 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1361211 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1499527 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1406259 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1567863 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1617940 (Python Code)

Max Activating Token Index: 218

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1371761 (Python Code)

Max Activating Token Index: 443

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1615503 (Python Code)

Max Activating Token Index: 410

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1615691 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1606308 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1599981 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1435034 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1625272 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1643070 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1626953 (Python Code)

Max Activating Token Index: 339

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1536619 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1585205 (Python Code)

Max Activating Token Index: 430

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1437008 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1426157 (Python Code)

Max Activating Token Index: 750