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

Dataset: The Pile

Neuron 1243 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: 5.3574. Min Range: -5.3574

Max Act: 5.3574. Min Act: -0.0000

Data Index: 745960 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 5.3574. Min Range: -5.3574

Max Act: 5.1505. Min Act: -0.0000

Data Index: 1175834 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 5.3574. Min Range: -5.3574

Max Act: 5.1048. Min Act: -0.0000

Data Index: 1071235 (The Pile)

Max Activating Token Index: 7

Text #3

Max Range: 5.3574. Min Range: -5.3574

Max Act: 5.2133. Min Act: -0.0000

Data Index: 193551 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.9997. Min Act: -0.0000

Data Index: 675110 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 5.3574. Min Range: -5.3574

Max Act: 5.1513. Min Act: -0.0000

Data Index: 456501 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.9062. Min Act: -0.0000

Data Index: 1358594 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.6828. Min Act: -0.0000

Data Index: 800905 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.8529. Min Act: -0.0000

Data Index: 1019365 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 5.3574. Min Range: -5.3574

Max Act: 5.3522. Min Act: -0.0000

Data Index: 1177366 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 5.3574. Min Range: -5.3574

Max Act: 5.1530. Min Act: -0.0000

Data Index: 1512242 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.9514. Min Act: -0.0000

Data Index: 976060 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.5303. Min Act: -0.0000

Data Index: 1937231 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.8906. Min Act: -0.0000

Data Index: 1024995 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.7057. Min Act: -0.0000

Data Index: 110148 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.6535. Min Act: -0.0000

Data Index: 385405 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.9739. Min Act: -0.0000

Data Index: 823245 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.7700. Min Act: -0.0000

Data Index: 833913 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 5.3574. Min Range: -5.3574

Max Act: 4.7419. Min Act: -0.0000

Data Index: 520012 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 5.3574. Min Range: -5.3574

Max Act: 5.1180. Min Act: -0.0000

Data Index: 441307 (The Pile)

Max Activating Token Index: 255