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

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

Neuron 1968 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: 1541991 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1629557 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1492919 (Python Code)

Max Activating Token Index: 986

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1378582 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1636340 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1481206 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1656654 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1644077 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1479603 (Python Code)

Max Activating Token Index: 683

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1530982 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 1469920 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1440077 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1602697 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1641800 (Python Code)

Max Activating Token Index: 670

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1489791 (Python Code)

Max Activating Token Index: 449

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1559859 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1560120 (Python Code)

Max Activating Token Index: 561

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1384331 (Python Code)

Max Activating Token Index: 628

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1411011 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1432425 (Python Code)

Max Activating Token Index: 607