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

Dataset: The Pile

Neuron 3496 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: 1.6065. Min Range: -1.6065

Max Act: 1.6065. Min Act: -0.0000

Data Index: 359393 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1113483 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1225. Min Act: -0.0000

Data Index: 1751722 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1236809 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1569. Min Act: -0.0000

Data Index: 189904 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1390. Min Act: -0.0000

Data Index: 1219919 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1989429 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.0706. Min Act: -0.0000

Data Index: 238629 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1460. Min Act: -0.0000

Data Index: 971964 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9519. Min Act: -0.0000

Data Index: 560422 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9392. Min Act: -0.0000

Data Index: 698426 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9347. Min Act: -0.0000

Data Index: 442523 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9251. Min Act: -0.0000

Data Index: 433335 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1207160 (The Pile)

Max Activating Token Index: 440

Text #14

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9624. Min Act: -0.0000

Data Index: 209261 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1814408 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1780341 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1368665 (The Pile)

Max Activating Token Index: 908

Text #18

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1872921 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.6065. Min Range: -1.6065

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1798997 (The Pile)

Max Activating Token Index: 758