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

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

Neuron 1449 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: 0.0099. Min Range: -0.0099

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1530593 (Python Code)

Max Activating Token Index: 389

Text #1

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1518871 (Python Code)

Max Activating Token Index: 289

Text #2

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1451787 (Python Code)

Max Activating Token Index: 245

Text #3

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1560900 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1648674 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1444468 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1598549 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1587161 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1450267 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1421661 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1501073 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1375651 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1564748 (Python Code)

Max Activating Token Index: 306

Text #13

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1431197 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1650129 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1498879 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1498632 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1396128 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1535218 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 0.0099. Min Range: -0.0099

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1597027 (Python Code)

Max Activating Token Index: 78