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

Dataset: The Pile

Neuron 4785 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: 0.0719. Min Range: -0.0719

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1026036 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1058903 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0668. Min Act: -0.0000

Data Index: 849491 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1780801 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1491206 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1168974 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1981274 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0599. Min Act: -0.0000

Data Index: 593484 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1336044 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0569. Min Act: -0.0000

Data Index: 152887 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1745572 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0557. Min Act: -0.0000

Data Index: 511746 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1952433 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0547. Min Act: -0.0000

Data Index: 81949 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0542. Min Act: -0.0000

Data Index: 866269 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1398034 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1887655 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0552. Min Act: -0.0000

Data Index: 643540 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0529. Min Act: -0.0000

Data Index: 487315 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1820272 (The Pile)

Max Activating Token Index: 1023