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

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

Neuron 2028 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: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0004

Data Index: 452812 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0100. Min Act: -0.0004

Data Index: 224778 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0004

Data Index: 1065871 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0097. Min Act: -0.0003

Data Index: 1623634 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0004

Data Index: 1157747 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1609175 (Python Code)

Max Activating Token Index: 93

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0004

Data Index: 669271 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0004

Data Index: 1004831 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1506564 (Python Code)

Max Activating Token Index: 164

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0003

Data Index: 749924 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1385684 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1393767 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1422092 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1427251 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1424532 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1408676 (Python Code)

Max Activating Token Index: 547

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0003

Data Index: 187583 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0003

Data Index: 168801 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0004

Data Index: 729502 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1471805 (Python Code)

Max Activating Token Index: 158