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

Dataset: The Pile

Neuron 519 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1560240 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.2109. Min Act: -0.0000

Data Index: 242724 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1952008 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1888242 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1099256 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1808415 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1768435 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1638. Min Act: -0.0000

Data Index: 309843 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1681. Min Act: -0.0000

Data Index: 827441 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1000364 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1185403 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1655229 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1373089 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1604062 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1405. Min Act: -0.0000

Data Index: 912936 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1515. Min Act: -0.0000

Data Index: 62503 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1417343 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1556. Min Act: -0.0000

Data Index: 51869 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1609. Min Act: -0.0000

Data Index: 482980 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 0.2270. Min Range: -0.2270

Max Act: 0.1435. Min Act: -0.0000

Data Index: 609925 (The Pile)

Max Activating Token Index: 291