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

Dataset: The Pile

Neuron 1948 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6882. Min Act: -0.0000

Data Index: 957594 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1245978 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6816. Min Act: -0.0000

Data Index: 123230 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1721374 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.7418. Min Act: -0.0000

Data Index: 966256 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6124. Min Act: -0.0000

Data Index: 585031 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6479. Min Act: -0.0000

Data Index: 448510 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1514073 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6658. Min Act: -0.0000

Data Index: 664428 (The Pile)

Max Activating Token Index: 950

Text #9

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6181. Min Act: -0.0000

Data Index: 97723 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1300999 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1515459 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1401766 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5175. Min Act: -0.0000

Data Index: 904967 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1125820 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5995. Min Act: -0.0000

Data Index: 5334 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1474657 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1671692 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1048344 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 0.7418. Min Range: -0.7418

Max Act: 0.5803. Min Act: -0.0000

Data Index: 233424 (The Pile)

Max Activating Token Index: 948