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

Dataset: The Pile

Neuron 1477 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: 1.9268. Min Range: -1.9268

Max Act: 1.8024. Min Act: -0.0000

Data Index: 1711129 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.8883. Min Act: -0.0000

Data Index: 862501 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.9268. Min Act: -0.0000

Data Index: 1755203 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1028537 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.8032. Min Act: -0.0000

Data Index: 1860530 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1526991 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1800419 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.7427. Min Act: -0.0000

Data Index: 1011847 (The Pile)

Max Activating Token Index: 771

Text #8

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.6924. Min Act: -0.0000

Data Index: 500725 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.7201. Min Act: -0.0000

Data Index: 1752418 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.6209. Min Act: -0.0000

Data Index: 1733025 (The Pile)

Max Activating Token Index: 458

Text #11

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1425730 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5953. Min Act: -0.0000

Data Index: 1183678 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.4429. Min Act: -0.0000

Data Index: 367040 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5258. Min Act: -0.0000

Data Index: 777396 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.4236. Min Act: -0.0000

Data Index: 1812430 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5018. Min Act: -0.0000

Data Index: 540582 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5794. Min Act: -0.0000

Data Index: 210079 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.4887. Min Act: -0.0000

Data Index: 1391633 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 1.9268. Min Range: -1.9268

Max Act: 1.5704. Min Act: -0.0000

Data Index: 238549 (The Pile)

Max Activating Token Index: 434