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

Dataset: The Pile

Neuron 3718 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: 1.7658. Min Range: -1.7658

Max Act: 1.7658. Min Act: -0.0000

Data Index: 1708340 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.4121. Min Act: -0.0000

Data Index: 699566 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2264. Min Act: -0.0000

Data Index: 292672 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.3818. Min Act: -0.0000

Data Index: 198826 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2871. Min Act: -0.0000

Data Index: 683612 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2869. Min Act: -0.0000

Data Index: 1846030 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1292294 (The Pile)

Max Activating Token Index: 76

Text #7

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1260296 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1746004 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1891321 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1801476 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2325. Min Act: -0.0000

Data Index: 171778 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2116. Min Act: -0.0000

Data Index: 138085 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1312585 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2147. Min Act: -0.0000

Data Index: 670251 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2816. Min Act: -0.0000

Data Index: 555424 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2014. Min Act: -0.0000

Data Index: 1326837 (The Pile)

Max Activating Token Index: 617

Text #17

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1038874 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.1754. Min Act: -0.0000

Data Index: 379711 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 1.7658. Min Range: -1.7658

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1559053 (The Pile)

Max Activating Token Index: 806