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

Dataset: The Pile

Neuron 696 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: 5.2640. Min Range: -5.2640

Max Act: 5.2640. Min Act: -0.0000

Data Index: 1615616 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 5.2640. Min Range: -5.2640

Max Act: 5.1811. Min Act: -0.0000

Data Index: 745555 (The Pile)

Max Activating Token Index: 621

Text #2

Max Range: 5.2640. Min Range: -5.2640

Max Act: 5.0964. Min Act: -0.0000

Data Index: 419683 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.7823. Min Act: -0.0000

Data Index: 1918764 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.9699. Min Act: -0.0000

Data Index: 127432 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.9052. Min Act: -0.0000

Data Index: 1298247 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.8935. Min Act: -0.0000

Data Index: 581648 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.7397. Min Act: -0.0000

Data Index: 1173097 (The Pile)

Max Activating Token Index: 305

Text #8

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.8876. Min Act: -0.0000

Data Index: 1621806 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.6612. Min Act: -0.0000

Data Index: 558180 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.6705. Min Act: -0.0000

Data Index: 1287412 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.8468. Min Act: -0.0000

Data Index: 646594 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.9937. Min Act: -0.0000

Data Index: 480339 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.8183. Min Act: -0.0000

Data Index: 822516 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.7693. Min Act: -0.0000

Data Index: 729131 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.7499. Min Act: -0.0000

Data Index: 490719 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.7504. Min Act: -0.0000

Data Index: 1578418 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.7361. Min Act: -0.0000

Data Index: 1859748 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.7148. Min Act: -0.0000

Data Index: 795319 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 5.2640. Min Range: -5.2640

Max Act: 4.5063. Min Act: -0.0000

Data Index: 928570 (The Pile)

Max Activating Token Index: 410