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

Dataset: The Pile

Neuron 4088 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.4815. Min Act: -0.0000

Data Index: 1863421 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.4955. Min Act: -0.0000

Data Index: 633751 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.4830. Min Act: -0.0000

Data Index: 161797 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.4232. Min Act: -0.0000

Data Index: 1406294 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1214284 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.4260. Min Act: -0.0000

Data Index: 717442 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.3586. Min Act: -0.0000

Data Index: 580600 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1698525 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2373. Min Act: -0.0000

Data Index: 441226 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2094. Min Act: -0.0000

Data Index: 797716 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.3057. Min Act: -0.0000

Data Index: 887693 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1494390 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1875139 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2071. Min Act: -0.0000

Data Index: 969184 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2484. Min Act: -0.0000

Data Index: 791546 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1538059 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1507790 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1457839 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1615657 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.4955. Min Range: -1.4955

Max Act: 1.2102. Min Act: -0.0000

Data Index: 358424 (The Pile)

Max Activating Token Index: 607