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

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

Neuron 1295 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4804. Min Range: -2.4804

Max Act: 2.4804. Min Act: -0.0000

Data Index: 1637100 (Python Code)

Max Activating Token Index: 325

Text #1

Max Range: 2.4804. Min Range: -2.4804

Max Act: 2.1316. Min Act: 0.0000

Data Index: 1521903 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 2.4804. Min Range: -2.4804

Max Act: 2.0700. Min Act: -0.0000

Data Index: 1492528 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.7654. Min Act: -0.0000

Data Index: 1397899 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.4901. Min Act: -0.0000

Data Index: 1383568 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.5454. Min Act: -0.0000

Data Index: 1519335 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1508692 (Python Code)

Max Activating Token Index: 201

Text #7

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1644620 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1478990 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1459052 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.4642. Min Act: -0.0000

Data Index: 1636711 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.3763. Min Act: -0.0000

Data Index: 1578137 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1605680 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1645008 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1538088 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.3730. Min Act: -0.0000

Data Index: 1432104 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1620960 (Python Code)

Max Activating Token Index: 313

Text #17

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1415989 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1407314 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 2.4804. Min Range: -2.4804

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1608289 (Python Code)

Max Activating Token Index: 923