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

Dataset: The Pile

Neuron 3402 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: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1335730 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1352941 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1917. Min Act: -0.0000

Data Index: 743621 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1781646 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1864. Min Act: -0.0000

Data Index: 589921 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1932. Min Act: -0.0000

Data Index: 302819 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1841. Min Act: -0.0000

Data Index: 818457 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1833. Min Act: -0.0000

Data Index: 600048 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1755. Min Act: -0.0000

Data Index: 121674 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1727. Min Act: -0.0000

Data Index: 753976 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1057509 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1699. Min Act: -0.0000

Data Index: 503098 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1678. Min Act: -0.0000

Data Index: 30696 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1879823 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1618. Min Act: -0.0000

Data Index: 194828 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1599. Min Act: -0.0000

Data Index: 495179 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1449313 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1680805 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1078893 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1934833 (The Pile)

Max Activating Token Index: 1023