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

Dataset: The Pile

Neuron 3476 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.1471. Min Act: -0.0000

Data Index: 226106 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0414. Min Act: -0.0000

Data Index: 718568 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1849078 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0593. Min Act: -0.0000

Data Index: 134051 (The Pile)

Max Activating Token Index: 530

Text #4

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1878987 (The Pile)

Max Activating Token Index: 47

Text #5

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1250870 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1360241 (The Pile)

Max Activating Token Index: 828

Text #7

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1246872 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1839264 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1730916 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9957. Min Act: -0.0000

Data Index: 734973 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1165115 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1105609 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1930227 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1785437 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9083. Min Act: -0.0000

Data Index: 326086 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8902. Min Act: -0.0000

Data Index: 14111 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9000. Min Act: -0.0000

Data Index: 109193 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1087874 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8889. Min Act: -0.0000

Data Index: 952402 (The Pile)

Max Activating Token Index: 320