Model: None

Dataset: The Pile

Neuron 2082 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.8320. Min Act: -0.1700

Data Index: 1104871 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7381. Min Act: -0.1700

Data Index: 7152353 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.7068. Min Act: -0.1700

Data Index: 5565529 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6755. Min Act: -0.1700

Data Index: 2934237 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6755. Min Act: -0.1700

Data Index: 10742435 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6755. Min Act: -0.1700

Data Index: 7860687 (The Pile)

Max Activating Token Index: 893

Text #6

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6599. Min Act: -0.1700

Data Index: 3837307 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6442. Min Act: -0.1700

Data Index: 3245169 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6129. Min Act: -0.1700

Data Index: 10488458 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.6129. Min Act: -0.1700

Data Index: 9005285 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5973. Min Act: -0.1700

Data Index: 3262668 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5973. Min Act: -0.1700

Data Index: 6515917 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5973. Min Act: -0.1700

Data Index: 5815225 (The Pile)

Max Activating Token Index: 550

Text #13

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5973. Min Act: -0.1700

Data Index: 2913178 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5816. Min Act: -0.1700

Data Index: 6468166 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5659. Min Act: -0.1700

Data Index: 3891482 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5659. Min Act: -0.1700

Data Index: 8584876 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5659. Min Act: -0.1700

Data Index: 5966187 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5503. Min Act: -0.1700

Data Index: 10349557 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 3.8320. Min Range: -3.8320

Max Act: 3.5503. Min Act: -0.1700

Data Index: 3427756 (The Pile)

Max Activating Token Index: 940