Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.3559. Min Act: -0.0000

Data Index: 672404 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.2101. Min Act: -0.0001

Data Index: 1612696 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.2112. Min Act: -0.0001

Data Index: 1290366 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1908. Min Act: -0.0001

Data Index: 1423431 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1863. Min Act: -0.0001

Data Index: 1561695 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1429. Min Act: -0.0000

Data Index: 728756 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1744. Min Act: -0.0001

Data Index: 1469506 (Python Code)

Max Activating Token Index: 963

Text #7

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0440. Min Act: -0.0000

Data Index: 184011 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1004. Min Act: -0.0001

Data Index: 1502661 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1784. Min Act: -0.0001

Data Index: 1396879 (Python Code)

Max Activating Token Index: 663

Text #10

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1265768 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0807. Min Act: -0.0000

Data Index: 347186 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0758. Min Act: -0.0001

Data Index: 460887 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0139. Min Act: -0.0001

Data Index: 1381561 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1539880 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9623. Min Act: -0.0001

Data Index: 1378867 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0012. Min Act: -0.0001

Data Index: 1619708 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0131. Min Act: -0.0001

Data Index: 1431429 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0044. Min Act: -0.0001

Data Index: 1584145 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0202. Min Act: -0.0000

Data Index: 802557 (C4 (Web Text))

Max Activating Token Index: 176