Model: None

Dataset: The Pile

Neuron 1704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')

Text #0

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3390. Min Act: -0.1700

Data Index: 4499283 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2605. Min Act: -0.1700

Data Index: 2065947 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2448. Min Act: -0.1700

Data Index: 9499677 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1661. Min Act: -0.1700

Data Index: 6742614 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1504. Min Act: -0.1700

Data Index: 2760064 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1504. Min Act: -0.1700

Data Index: 2644271 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1346. Min Act: -0.1700

Data Index: 814007 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1346. Min Act: -0.1700

Data Index: 3911153 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1189. Min Act: -0.1700

Data Index: 2053900 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1189. Min Act: -0.1700

Data Index: 5614586 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1031. Min Act: -0.1700

Data Index: 3787684 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0715. Min Act: -0.1700

Data Index: 3822549 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0715. Min Act: -0.1700

Data Index: 2346445 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0715. Min Act: -0.1700

Data Index: 3882958 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0558. Min Act: -0.1700

Data Index: 6301899 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0558. Min Act: -0.1700

Data Index: 5406819 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0558. Min Act: -0.1700

Data Index: 3128537 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0558. Min Act: -0.1700

Data Index: 8575579 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0558. Min Act: -0.1700

Data Index: 245184 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.0400. Min Act: -0.1700

Data Index: 4215936 (The Pile)

Max Activating Token Index: 885