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

Dataset: The Pile

Neuron 3710 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: 0.9945. Min Range: -0.9945

Max Act: 0.9787. Min Act: -0.0000

Data Index: 514249 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1861145 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8864. Min Act: -0.0000

Data Index: 1444702 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9352. Min Act: -0.0000

Data Index: 23247 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1680720 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7809. Min Act: -0.0000

Data Index: 144817 (The Pile)

Max Activating Token Index: 535

Text #6

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7484. Min Act: -0.0000

Data Index: 946579 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1972615 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1812331 (The Pile)

Max Activating Token Index: 5

Text #9

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7652. Min Act: -0.0000

Data Index: 924720 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1216208 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6704. Min Act: -0.0000

Data Index: 647378 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6584. Min Act: -0.0000

Data Index: 776903 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1462522 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6728. Min Act: -0.0000

Data Index: 838574 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5741. Min Act: -0.0000

Data Index: 396666 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7710. Min Act: -0.0000

Data Index: 703680 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1439865 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7129. Min Act: -0.0000

Data Index: 311826 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7065. Min Act: 0.0000

Data Index: 1724175 (The Pile)

Max Activating Token Index: 764