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

Dataset: The Pile

Neuron 88 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.8417. Min Act: -0.0000

Data Index: 669349 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7851. Min Act: -0.0000

Data Index: 359299 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7623. Min Act: -0.0000

Data Index: 1959558 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7776. Min Act: -0.0000

Data Index: 528112 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1470546 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1886841 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6888. Min Act: -0.0000

Data Index: 596666 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6596. Min Act: -0.0000

Data Index: 943615 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1693359 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6638. Min Act: -0.0000

Data Index: 300906 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6553. Min Act: -0.0000

Data Index: 835741 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6501. Min Act: -0.0000

Data Index: 981917 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1657759 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5652. Min Act: -0.0000

Data Index: 422917 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6375. Min Act: -0.0000

Data Index: 409358 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6044. Min Act: -0.0000

Data Index: 985774 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1075800 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1357329 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6085. Min Act: -0.0000

Data Index: 940199 (The Pile)

Max Activating Token Index: 47

Text #19

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.5981. Min Act: -0.0000

Data Index: 998585 (The Pile)

Max Activating Token Index: 839