Model: None

Dataset: The Pile

Neuron 1384 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.3390. Min Act: -0.1700

Data Index: 7419284 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2919. Min Act: -0.1700

Data Index: 4463256 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2604. Min Act: -0.1700

Data Index: 6033393 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2447. Min Act: -0.1700

Data Index: 7859970 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2447. Min Act: -0.1700

Data Index: 10424656 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2290. Min Act: -0.1700

Data Index: 157500 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2290. Min Act: -0.1700

Data Index: 4819191 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.2133. Min Act: -0.1700

Data Index: 4950474 (The Pile)

Max Activating Token Index: 253

Text #8

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1975. Min Act: -0.1700

Data Index: 10153507 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1975. Min Act: -0.1700

Data Index: 8176137 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1818. Min Act: -0.1700

Data Index: 3078697 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1818. Min Act: -0.1700

Data Index: 4725714 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1818. Min Act: -0.1700

Data Index: 8330604 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1661. Min Act: -0.1700

Data Index: 1581551 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1503. Min Act: -0.1700

Data Index: 1410326 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1346. Min Act: -0.1700

Data Index: 5004822 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1188. Min Act: -0.1700

Data Index: 7485018 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1188. Min Act: -0.1700

Data Index: 7675914 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1188. Min Act: -0.1700

Data Index: 8427860 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 3.3390. Min Range: -3.3390

Max Act: 3.1188. Min Act: -0.1700

Data Index: 8504173 (The Pile)

Max Activating Token Index: 782