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

Dataset: The Pile

Neuron 1971 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2600. Min Range: -1.2600

Max Act: 1.2600. Min Act: -0.0000

Data Index: 48182 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 1.2600. Min Range: -1.2600

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1646356 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9812. Min Act: -0.0000

Data Index: 232608 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9955. Min Act: -0.0000

Data Index: 356224 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1830359 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1311618 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9732. Min Act: -0.0000

Data Index: 473921 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9399. Min Act: -0.0000

Data Index: 547675 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1217914 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9192. Min Act: -0.0000

Data Index: 385419 (The Pile)

Max Activating Token Index: 931

Text #10

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9172. Min Act: -0.0000

Data Index: 56005 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1156919 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1936228 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8962. Min Act: -0.0000

Data Index: 258702 (The Pile)

Max Activating Token Index: 868

Text #14

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1956442 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8711. Min Act: -0.0000

Data Index: 130722 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8865. Min Act: -0.0000

Data Index: 78789 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.9101. Min Act: -0.0000

Data Index: 371656 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8830. Min Act: -0.0000

Data Index: 117257 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 1.2600. Min Range: -1.2600

Max Act: 0.8782. Min Act: -0.0000

Data Index: 740452 (The Pile)

Max Activating Token Index: 472