Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7853. Min Act: -0.0000

Data Index: 295397 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1021478 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7646. Min Act: -0.0000

Data Index: 8781 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.8118. Min Act: -0.0000

Data Index: 170005 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1520416 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1474362 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7497. Min Act: -0.0000

Data Index: 189704 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1796463 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1398813 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1202907 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1424335 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1563511 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1592863 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7033. Min Act: -0.0000

Data Index: 409519 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1855282 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1496959 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1996957 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1837776 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1104975 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 0.8314. Min Range: -0.8314

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1074902 (The Pile)

Max Activating Token Index: 40