Model: None

Dataset: The Pile

Neuron 965 in Layer 16

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.1016. Min Act: -0.1700

Data Index: 6897058 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0858. Min Act: -0.1700

Data Index: 6186467 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0858. Min Act: -0.1700

Data Index: 5445016 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0858. Min Act: -0.1700

Data Index: 6313918 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0858. Min Act: -0.1700

Data Index: 6484003 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0700. Min Act: -0.1700

Data Index: 5281033 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0700. Min Act: -0.1700

Data Index: 5704286 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0542. Min Act: -0.1700

Data Index: 8841421 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0542. Min Act: -0.1700

Data Index: 2917531 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0542. Min Act: -0.1700

Data Index: 203411 (The Pile)

Max Activating Token Index: 187

Text #10

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0384. Min Act: -0.1700

Data Index: 7236834 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0384. Min Act: -0.1700

Data Index: 5972034 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0384. Min Act: -0.1700

Data Index: 843124 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0384. Min Act: -0.1700

Data Index: 6561214 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0384. Min Act: -0.1700

Data Index: 782305 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0226. Min Act: -0.1700

Data Index: 5572546 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0226. Min Act: -0.1700

Data Index: 10507568 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0226. Min Act: -0.1700

Data Index: 9290405 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0226. Min Act: -0.1700

Data Index: 3869813 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0068. Min Act: -0.1700

Data Index: 1947472 (The Pile)

Max Activating Token Index: 561