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

Dataset: The Pile

Neuron 1284 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: 8.8016. Min Range: -8.8016

Max Act: 8.6417. Min Act: -0.0000

Data Index: 952667 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.8016. Min Act: -0.0000

Data Index: 230855 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.1534. Min Act: -0.0000

Data Index: 297141 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.1242. Min Act: -0.0000

Data Index: 537066 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.3349. Min Act: -0.0000

Data Index: 1308631 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.1063. Min Act: -0.0000

Data Index: 843070 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.1954. Min Act: -0.0000

Data Index: 843997 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.3606. Min Act: -0.0000

Data Index: 101883 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.8952. Min Act: -0.0000

Data Index: 427241 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.8705. Min Act: -0.0000

Data Index: 987015 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.0637. Min Act: -0.0000

Data Index: 1779040 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.8379. Min Act: -0.0000

Data Index: 356792 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.8282. Min Act: -0.0000

Data Index: 1267067 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.3268. Min Act: -0.0000

Data Index: 712353 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.9490. Min Act: -0.0000

Data Index: 232749 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.9414. Min Act: -0.0000

Data Index: 1910551 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.9266. Min Act: -0.0000

Data Index: 1263657 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 8.8016. Min Range: -8.8016

Max Act: 8.1103. Min Act: -0.0000

Data Index: 126926 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.8587. Min Act: -0.0000

Data Index: 870345 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 8.8016. Min Range: -8.8016

Max Act: 7.6348. Min Act: -0.0000

Data Index: 527004 (The Pile)

Max Activating Token Index: 552