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

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

Neuron 1060 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: 0.3480. Min Range: -0.3480

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1049418 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2796. Min Act: -0.0000

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1236593 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1535744 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2520. Min Act: -0.0000

Data Index: 880454 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2425. Min Act: -0.0000

Data Index: 686893 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1484880 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2173. Min Act: -0.0000

Data Index: 843468 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1593511 (Python Code)

Max Activating Token Index: 715

Text #9

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1525472 (Python Code)

Max Activating Token Index: 668

Text #10

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1366938 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1557216 (Python Code)

Max Activating Token Index: 999

Text #12

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1607012 (Python Code)

Max Activating Token Index: 75

Text #13

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1641768 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1516714 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1380865 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1436169 (Python Code)

Max Activating Token Index: 537

Text #17

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2212. Min Act: -0.0000

Data Index: 491158 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.2170. Min Act: -0.0000

Data Index: 944845 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.3480. Min Range: -0.3480

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1475412 (Python Code)

Max Activating Token Index: 223