Model: None

Dataset: The Pile

Neuron 3647 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1016. Min Range: -4.1016

Max Act: 4.1016. Min Act: -0.1700

Data Index: 6880627 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 4.1016. Min Range: -4.1016

Max Act: 4.0391. Min Act: -0.1700

Data Index: 4987375 (The Pile)

Max Activating Token Index: 611

Text #2

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.9766. Min Act: -0.1700

Data Index: 3887952 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.8984. Min Act: -0.1700

Data Index: 179306 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.8828. Min Act: -0.1700

Data Index: 2574507 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.8046. Min Act: -0.1700

Data Index: 2999248 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.8046. Min Act: -0.1700

Data Index: 4603868 (The Pile)

Max Activating Token Index: 438

Text #7

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.8046. Min Act: -0.1700

Data Index: 3300478 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7889. Min Act: -0.1700

Data Index: 600549 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7577. Min Act: -0.1700

Data Index: 3126707 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7577. Min Act: -0.1700

Data Index: 6756996 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7420. Min Act: -0.1700

Data Index: 4383554 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7420. Min Act: -0.1700

Data Index: 8234067 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7264. Min Act: -0.1700

Data Index: 2958468 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7264. Min Act: -0.1700

Data Index: 4183280 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.7107. Min Act: -0.1700

Data Index: 7735935 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.6951. Min Act: -0.1700

Data Index: 3183935 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.6951. Min Act: -0.1700

Data Index: 5924015 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.6794. Min Act: -0.1700

Data Index: 4237588 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 4.1016. Min Range: -4.1016

Max Act: 3.6794. Min Act: -0.1700

Data Index: 5071069 (The Pile)

Max Activating Token Index: 647