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

Dataset: The Pile

Neuron 4075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1143260 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.4689. Min Act: -0.0000

Data Index: 115542 (The Pile)

Max Activating Token Index: 907

Text #2

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.3487. Min Act: -0.0000

Data Index: 332686 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1665573 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.2579. Min Act: -0.0000

Data Index: 940419 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1497065 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1869513 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1569518 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 1.5012. Min Range: -1.5012

Max Act: 0.9696. Min Act: -0.0000

Data Index: 800281 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.2702. Min Act: -0.0000

Data Index: 611368 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1924662 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1757. Min Act: -0.0000

Data Index: 49512 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1375524 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1240. Min Act: -0.0000

Data Index: 459304 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1533. Min Act: -0.0000

Data Index: 1559232 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1513. Min Act: -0.0000

Data Index: 318666 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1717. Min Act: -0.0000

Data Index: 43499 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1018. Min Act: -0.0000

Data Index: 222383 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.0760. Min Act: -0.0000

Data Index: 1354616 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 1.5012. Min Range: -1.5012

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1891644 (The Pile)

Max Activating Token Index: 483