Model: None

Dataset: The Pile

Neuron 1800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')

Text #0

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.8320. Min Act: -0.1700

Data Index: 1598704 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.8320. Min Act: -0.1700

Data Index: 8823950 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.7070. Min Act: -0.1700

Data Index: 2684818 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.7070. Min Act: -0.1700

Data Index: 1330852 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.7070. Min Act: -0.1700

Data Index: 3534687 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6757. Min Act: -0.1700

Data Index: 6259426 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6757. Min Act: -0.1700

Data Index: 6321181 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6445. Min Act: -0.1700

Data Index: 4426447 (The Pile)

Max Activating Token Index: 892

Text #8

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6445. Min Act: -0.1700

Data Index: 5614569 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6445. Min Act: -0.1700

Data Index: 10754401 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6445. Min Act: -0.1700

Data Index: 5539008 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6132. Min Act: -0.1700

Data Index: 10787191 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6132. Min Act: -0.1700

Data Index: 8459174 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6132. Min Act: -0.1700

Data Index: 1541671 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6132. Min Act: -0.1700

Data Index: 7841666 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6132. Min Act: -0.1700

Data Index: 1307295 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6132. Min Act: -0.1700

Data Index: 2243149 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.6132. Min Act: -0.1700

Data Index: 5601267 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.5820. Min Act: -0.1700

Data Index: 4399309 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 5.8320. Min Range: -5.8320

Max Act: 5.5820. Min Act: -0.1700

Data Index: 8501083 (The Pile)

Max Activating Token Index: 284