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

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

Neuron 229 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: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1575771 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1402323 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1506126 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1451878 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1469791 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1567982 (Python Code)

Max Activating Token Index: 912

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1449111 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1603619 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1456534 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1626716 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1560727 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0384. Min Act: -0.0002

Data Index: 282750 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1404204 (Python Code)

Max Activating Token Index: 171

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1626704 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1607835 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1557932 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1468686 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1407611 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1480563 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1514217 (Python Code)

Max Activating Token Index: 61