Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1712 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1483508 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1568446 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1468961 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1482772 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1502656 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1640520 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1605170 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1461512 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1584870 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1525499 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1541923 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1656628 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1435833 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1574133 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1532730 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1494158 (Python Code)

Max Activating Token Index: 233

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1656921 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1536091 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1489253 (Python Code)

Max Activating Token Index: 50

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1382786 (Python Code)

Max Activating Token Index: 4