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

Dataset: The Pile

Neuron 1347 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: 1.3487. Min Range: -1.3487

Max Act: 1.3487. Min Act: -0.0000

Data Index: 697822 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 1.3487. Min Range: -1.3487

Max Act: 1.1514. Min Act: -0.0000

Data Index: 782669 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1887798 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1714510 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1016211 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1668799 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8131. Min Act: -0.0000

Data Index: 695993 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8635. Min Act: -0.0000

Data Index: 31188 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1581047 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1629255 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1219122 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1902753 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1168833 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7329. Min Act: -0.0000

Data Index: 145489 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1784154 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6767. Min Act: -0.0000

Data Index: 102415 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7326. Min Act: -0.0000

Data Index: 11009 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1823829 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.8834. Min Act: -0.0000

Data Index: 419107 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 1.3487. Min Range: -1.3487

Max Act: 0.6622. Min Act: -0.0000

Data Index: 269189 (The Pile)

Max Activating Token Index: 324