Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2998 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.2004. Min Act: -0.0000

Data Index: 1461431 (Python Code)

Max Activating Token Index: 396

Text #1

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.3758. Min Act: -0.0000

Data Index: 1618015 (Python Code)

Max Activating Token Index: 314

Text #2

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1431690 (Python Code)

Max Activating Token Index: 536

Text #3

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.9898. Min Act: -0.0000

Data Index: 1469392 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.0649. Min Act: -0.0000

Data Index: 1428755 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.0601. Min Act: -0.0000

Data Index: 1641237 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.9408. Min Act: -0.0000

Data Index: 1538571 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8884. Min Act: -0.0000

Data Index: 1565280 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8600. Min Act: -0.0000

Data Index: 1580640 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8562. Min Act: -0.0000

Data Index: 1486135 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8136. Min Act: -0.0000

Data Index: 1389345 (Python Code)

Max Activating Token Index: 851

Text #11

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8164. Min Act: -0.0000

Data Index: 1554721 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1403464 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.7838. Min Act: -0.0000

Data Index: 1606402 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.6849. Min Act: -0.0000

Data Index: 1534935 (Python Code)

Max Activating Token Index: 225

Text #15

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1545094 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.7033. Min Act: -0.0000

Data Index: 1434015 (Python Code)

Max Activating Token Index: 875

Text #17

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.6032. Min Act: -0.0000

Data Index: 1583810 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1433146 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1374204 (Python Code)

Max Activating Token Index: 180