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

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

Neuron 4656 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1433050 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 1.1847. Min Range: -1.1847

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1580658 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 1.1847. Min Range: -1.1847

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1489771 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 1.1847. Min Range: -1.1847

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1364950 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.9591. Min Act: -0.0000

Data Index: 840052 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.9265. Min Act: -0.0000

Data Index: 463114 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1415926 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1569348 (Python Code)

Max Activating Token Index: 371

Text #8

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1588888 (Python Code)

Max Activating Token Index: 972

Text #9

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1478238 (Python Code)

Max Activating Token Index: 806

Text #10

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1469622 (Python Code)

Max Activating Token Index: 671

Text #11

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1446308 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1585695 (Python Code)

Max Activating Token Index: 113

Text #13

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1608402 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1399258 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1374324 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1212635 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1501184 (Python Code)

Max Activating Token Index: 321

Text #18

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1567492 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 1.1847. Min Range: -1.1847

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1563894 (Python Code)

Max Activating Token Index: 818