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

Dataset: The Pile

Neuron 1162 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0701. Min Range: -1.0701

Max Act: 1.0369. Min Act: -0.0000

Data Index: 599220 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 1.0701. Min Range: -1.0701

Max Act: 1.0605. Min Act: -0.0000

Data Index: 166470 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 1.0701. Min Range: -1.0701

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1768025 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.0701. Min Range: -1.0701

Max Act: 1.0226. Min Act: -0.0000

Data Index: 342821 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 1.0701. Min Range: -1.0701

Max Act: 1.0232. Min Act: -0.0000

Data Index: 985065 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1039622 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1426718 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1102421 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8136. Min Act: -0.0000

Data Index: 958537 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8041. Min Act: -0.0000

Data Index: 961066 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8419. Min Act: -0.0000

Data Index: 784905 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1931221 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7478. Min Act: -0.0000

Data Index: 52994 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.8103. Min Act: -0.0000

Data Index: 836153 (The Pile)

Max Activating Token Index: 282

Text #14

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1005200 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7659. Min Act: -0.0000

Data Index: 762322 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7344. Min Act: -0.0001

Data Index: 1654118 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1630819 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1008673 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.0701. Min Range: -1.0701

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1109687 (The Pile)

Max Activating Token Index: 415