Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 943 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1136119 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1491769 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1966. Min Act: -0.0000

Data Index: 56789 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1858. Min Act: -0.0000

Data Index: 387265 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1345892 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1723. Min Act: -0.0000

Data Index: 738980 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1264873 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1417745 (Python Code)

Max Activating Token Index: 366

Text #8

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1619264 (Python Code)

Max Activating Token Index: 898

Text #9

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1680. Min Act: -0.0000

Data Index: 370134 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1608. Min Act: -0.0000

Data Index: 491451 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1267839 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1553152 (Python Code)

Max Activating Token Index: 375

Text #13

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1718. Min Act: -0.0000

Data Index: 943533 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1479. Min Act: -0.0000

Data Index: 929617 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1490371 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1328837 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1552. Min Act: -0.0000

Data Index: 786067 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1270874 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.2071. Min Range: -0.2071

Max Act: 0.1510. Min Act: -0.0000

Data Index: 893602 (C4 (Web Text))

Max Activating Token Index: 661