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

Dataset: The Pile

Neuron 318 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1591. Min Act: 0.0000

Data Index: 44765 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1569. Min Act: 0.0000

Data Index: 1442637 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1564. Min Act: 0.0000

Data Index: 49662 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1560. Min Act: 0.0000

Data Index: 653379 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1552. Min Act: 0.0000

Data Index: 652381 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1550. Min Act: 0.0000

Data Index: 1844072 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1549. Min Act: 0.0000

Data Index: 384205 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1542. Min Act: 0.0000

Data Index: 1902812 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1541. Min Act: -0.0000

Data Index: 77938 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1570149 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1530. Min Act: 0.0000

Data Index: 1653372 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1523. Min Act: -0.0000

Data Index: 829321 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1526. Min Act: 0.0000

Data Index: 927230 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1844771 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1513. Min Act: 0.0000

Data Index: 868043 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1514. Min Act: 0.0000

Data Index: 1738353 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1458. Min Act: 0.0000

Data Index: 340822 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1512. Min Act: 0.0000

Data Index: 968759 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1510. Min Act: 0.0000

Data Index: 117412 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1591. Min Range: -0.1591

Max Act: 0.1504. Min Act: 0.0000

Data Index: 1043064 (The Pile)

Max Activating Token Index: 1023