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

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

Neuron 3871 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.4430. Min Act: -0.0000

Data Index: 1500825 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1603822 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3296. Min Act: -0.0000

Data Index: 1605919 (Python Code)

Max Activating Token Index: 352

Text #3

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1505633 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1521623 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1642438 (Python Code)

Max Activating Token Index: 951

Text #6

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1647960 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1413527 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1453784 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1635385 (Python Code)

Max Activating Token Index: 982

Text #10

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9538. Min Act: 0.0000

Data Index: 1531981 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1546731 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1456868 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9743. Min Act: 0.0000

Data Index: 1492161 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1422724 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1532661 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1437131 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9236. Min Act: 0.0000

Data Index: 1383687 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1374994 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1618493 (Python Code)

Max Activating Token Index: 820