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

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

Neuron 4958 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.9419. Min Act: -0.0000

Data Index: 1523586 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5536. Min Act: -0.0000

Data Index: 1641488 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4761. Min Act: -0.0000

Data Index: 1642822 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5090. Min Act: -0.0000

Data Index: 1472613 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1569650 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4946. Min Act: -0.0001

Data Index: 1415507 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1516478 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4652. Min Act: -0.0001

Data Index: 1398726 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1505032 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1587370 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1537160 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4692. Min Act: -0.0000

Data Index: 1485345 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.3058. Min Act: -0.0000

Data Index: 190770 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.4172. Min Act: -0.0001

Data Index: 1531563 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1607762 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.2913. Min Act: -0.0000

Data Index: 1508889 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1513108 (Python Code)

Max Activating Token Index: 753

Text #17

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1544081 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.1793. Min Act: -0.0001

Data Index: 991448 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.2281. Min Act: -0.0001

Data Index: 1614620 (Python Code)

Max Activating Token Index: 124