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

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

Neuron 3365 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1455533 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1493005 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1441053 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1492263 (Python Code)

Max Activating Token Index: 582

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1616588 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1535927 (Python Code)

Max Activating Token Index: 237

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1605327 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1518454 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1495701 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1303200 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1622330 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1469302 (Python Code)

Max Activating Token Index: 516

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1613992 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1607576 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1529995 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1512249 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1378467 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1461886 (Python Code)

Max Activating Token Index: 696

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1650887 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1375969 (Python Code)

Max Activating Token Index: 70