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

Dataset: The Pile

Neuron 1385 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: 1.0581. Min Range: -1.0581

Max Act: 1.0581. Min Act: -0.0000

Data Index: 119751 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 1.0581. Min Range: -1.0581

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1849670 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1264636 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1643025 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1645250 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1302677 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1515715 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8230. Min Act: -0.0000

Data Index: 581758 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1634662 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1619766 (The Pile)

Max Activating Token Index: 501

Text #10

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1322306 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1314846 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1421595 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1837591 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1520236 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1937863 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.8114. Min Act: -0.0000

Data Index: 897652 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7539. Min Act: -0.0000

Data Index: 480607 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7709. Min Act: -0.0001

Data Index: 877697 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 1.0581. Min Range: -1.0581

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1068767 (The Pile)

Max Activating Token Index: 88