Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2451 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1205937 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2575. Min Act: -0.0000

Data Index: 699424 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2476. Min Act: -0.0000

Data Index: 282536 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1712571 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2137. Min Act: -0.0000

Data Index: 68613 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2174. Min Act: -0.0000

Data Index: 505672 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1919. Min Act: -0.0000

Data Index: 502731 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1852. Min Act: -0.0000

Data Index: 470073 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1738107 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1895. Min Act: -0.0000

Data Index: 830310 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1983. Min Act: -0.0000

Data Index: 935651 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1882. Min Act: -0.0000

Data Index: 232703 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1658. Min Act: -0.0000

Data Index: 157242 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1600272 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2040. Min Act: -0.0000

Data Index: 330606 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1596747 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2025. Min Act: -0.0000

Data Index: 570258 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1011126 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1927301 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1812. Min Act: -0.0000

Data Index: 751238 (The Pile)

Max Activating Token Index: 304