Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3965 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.4504. Min Act: -0.0000

Data Index: 1794468 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.4481. Min Act: -0.0000

Data Index: 838761 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.3645. Min Act: -0.0000

Data Index: 191487 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2122. Min Act: -0.0000

Data Index: 456439 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.3648. Min Act: -0.0000

Data Index: 519317 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.3595. Min Act: -0.0000

Data Index: 311954 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.4146. Min Act: -0.0000

Data Index: 195359 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.4457. Min Act: -0.0000

Data Index: 1309213 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1903. Min Act: -0.0000

Data Index: 633471 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1840. Min Act: -0.0000

Data Index: 841903 (The Pile)

Max Activating Token Index: 22

Text #10

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2633. Min Act: -0.0000

Data Index: 620789 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2125. Min Act: -0.0000

Data Index: 582432 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2937. Min Act: -0.0000

Data Index: 54462 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1953283 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1799. Min Act: -0.0000

Data Index: 349867 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1996. Min Act: -0.0000

Data Index: 1578417 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1439391 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1823990 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1204537 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 1.4504. Min Range: -1.4504

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1274640 (The Pile)

Max Activating Token Index: 750