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

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

Neuron 3620 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1574773 (Python Code)

Max Activating Token Index: 185

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1424108 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1479261 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1471866 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1559332 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1546206 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1384752 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1524008 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1479130 (Python Code)

Max Activating Token Index: 294

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1574286 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1451695 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1575287 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1619812 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1481052 (Python Code)

Max Activating Token Index: 595

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1633456 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1609181 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1547947 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0399. Min Act: -0.0002

Data Index: 924979 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1555520 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0374. Min Act: -0.0003

Data Index: 606698 (C4 (Web Text))

Max Activating Token Index: 7