Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 811 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2348. Min Range: -2.2348

Max Act: 2.2348. Min Act: -0.0000

Data Index: 1557318 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 2.2348. Min Range: -2.2348

Max Act: 2.0910. Min Act: -0.0000

Data Index: 1654896 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 2.2348. Min Range: -2.2348

Max Act: 2.1636. Min Act: -0.0000

Data Index: 1532901 (Python Code)

Max Activating Token Index: 233

Text #3

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.9982. Min Act: -0.0000

Data Index: 1595503 (Python Code)

Max Activating Token Index: 331

Text #4

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.9624. Min Act: -0.0000

Data Index: 1558334 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 2.2348. Min Range: -2.2348

Max Act: 2.0388. Min Act: -0.0000

Data Index: 1564951 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1453645 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7961. Min Act: -0.0000

Data Index: 1484695 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7526. Min Act: -0.0000

Data Index: 1495808 (Python Code)

Max Activating Token Index: 513

Text #9

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7504. Min Act: -0.0000

Data Index: 1653222 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.8350. Min Act: -0.0000

Data Index: 1368626 (Python Code)

Max Activating Token Index: 945

Text #11

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.8328. Min Act: -0.0000

Data Index: 1489679 (Python Code)

Max Activating Token Index: 529

Text #12

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.9166. Min Act: -0.0000

Data Index: 1359891 (Python Code)

Max Activating Token Index: 936

Text #13

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7068. Min Act: -0.0000

Data Index: 1647085 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1480773 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.8058. Min Act: -0.0000

Data Index: 1391093 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7760. Min Act: -0.0000

Data Index: 1635756 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7762. Min Act: -0.0000

Data Index: 1648608 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1617981 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 2.2348. Min Range: -2.2348

Max Act: 1.7582. Min Act: -0.0000

Data Index: 1464253 (Python Code)

Max Activating Token Index: 822