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

Dataset: The Pile

Neuron 539 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: 1.3285. Min Range: -1.3285

Max Act: 1.3285. Min Act: -0.0000

Data Index: 454429 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.2075. Min Act: -0.0000

Data Index: 1123046 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.2001. Min Act: -0.0000

Data Index: 214626 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.2110. Min Act: -0.0000

Data Index: 841376 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0910. Min Act: -0.0000

Data Index: 437011 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1388221 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1609122 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0787. Min Act: -0.0000

Data Index: 866210 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1469267 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8485. Min Act: -0.0000

Data Index: 15642 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1807243 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9925. Min Act: -0.0000

Data Index: 392516 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1965004 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9529. Min Act: -0.0000

Data Index: 742358 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1072911 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1690591 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9389. Min Act: -0.0000

Data Index: 106743 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1574983 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1386461 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1300804 (The Pile)

Max Activating Token Index: 230