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

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

Neuron 123 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: 2.0776. Min Range: -2.0776

Max Act: 2.0776. Min Act: -0.0000

Data Index: 1524425 (Python Code)

Max Activating Token Index: 767

Text #1

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.9100. Min Act: -0.0000

Data Index: 1407657 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.8710. Min Act: -0.0000

Data Index: 1520803 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.7205. Min Act: -0.0000

Data Index: 1536333 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.7518. Min Act: -0.0000

Data Index: 1593834 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1463066 (Python Code)

Max Activating Token Index: 915

Text #6

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.7035. Min Act: -0.0000

Data Index: 1373155 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5332. Min Act: -0.0000

Data Index: 1550082 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.6462. Min Act: -0.0000

Data Index: 1619032 (Python Code)

Max Activating Token Index: 668

Text #9

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5942. Min Act: -0.0000

Data Index: 1368187 (Python Code)

Max Activating Token Index: 357

Text #10

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1602441 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1436437 (Python Code)

Max Activating Token Index: 731

Text #12

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.4246. Min Act: -0.0000

Data Index: 1363275 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5294. Min Act: -0.0000

Data Index: 1634440 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5431. Min Act: -0.0000

Data Index: 1588865 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1451974 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5149. Min Act: -0.0000

Data Index: 1384206 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1606283 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1557248 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 2.0776. Min Range: -2.0776

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1538727 (Python Code)

Max Activating Token Index: 129