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

Dataset: The Pile

Neuron 2554 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: 5.0668. Min Range: -5.0668

Max Act: 5.0668. Min Act: -0.0000

Data Index: 1620530 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.5419. Min Act: -0.0000

Data Index: 1986532 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.3076. Min Act: -0.0000

Data Index: 1290584 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2403. Min Act: -0.0000

Data Index: 1929342 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.4185. Min Act: -0.0000

Data Index: 109299 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.3253. Min Act: -0.0000

Data Index: 903761 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1373. Min Act: -0.0000

Data Index: 1683410 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1723. Min Act: -0.0000

Data Index: 1061303 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2435. Min Act: -0.0000

Data Index: 973965 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.0427. Min Act: -0.0000

Data Index: 1917535 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1053. Min Act: -0.0000

Data Index: 896757 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2813. Min Act: -0.0000

Data Index: 1274526 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 5.0668. Min Range: -5.0668

Max Act: 3.9332. Min Act: -0.0000

Data Index: 1297029 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.0774. Min Act: -0.0000

Data Index: 992638 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 5.0668. Min Range: -5.0668

Max Act: 3.9110. Min Act: -0.0000

Data Index: 1494426 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 5.0668. Min Range: -5.0668

Max Act: 3.8728. Min Act: -0.0000

Data Index: 1092187 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 5.0668. Min Range: -5.0668

Max Act: 3.8213. Min Act: -0.0000

Data Index: 657231 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 5.0668. Min Range: -5.0668

Max Act: 3.8042. Min Act: -0.0000

Data Index: 152209 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1123. Min Act: -0.0000

Data Index: 24019 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 5.0668. Min Range: -5.0668

Max Act: 3.9110. Min Act: -0.0000

Data Index: 1337334 (The Pile)

Max Activating Token Index: 281