Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3008 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0733. Min Range: -1.0733

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1242116 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1485976 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1700239 (The Pile)

Max Activating Token Index: 526

Text #3

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1138258 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1282458 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.8104. Min Act: -0.0000

Data Index: 640082 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1901857 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7544. Min Act: -0.0000

Data Index: 52709 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7509. Min Act: -0.0000

Data Index: 508525 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7798. Min Act: -0.0000

Data Index: 692619 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1647981 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1782015 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1361373 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7802. Min Act: -0.0000

Data Index: 223162 (The Pile)

Max Activating Token Index: 242

Text #14

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.6989. Min Act: -0.0000

Data Index: 892326 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1077359 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7175. Min Act: -0.0000

Data Index: 873981 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7594. Min Act: -0.0001

Data Index: 524712 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.7287. Min Act: -0.0000

Data Index: 372711 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 1.0733. Min Range: -1.0733

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1121178 (The Pile)

Max Activating Token Index: 290