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

Dataset: The Pile

Neuron 41 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.6057. Min Act: -0.0000

Data Index: 379284 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4010. Min Act: -0.0000

Data Index: 430590 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4479. Min Act: -0.0000

Data Index: 814155 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1343662 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2707. Min Act: -0.0000

Data Index: 319039 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3512. Min Act: -0.0000

Data Index: 1736283 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1204223 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1977. Min Act: 0.0000

Data Index: 1698648 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1073. Min Act: -0.0000

Data Index: 39624 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2148. Min Act: -0.0000

Data Index: 348099 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1943565 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2373. Min Act: 0.0000

Data Index: 1703289 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1070. Min Act: -0.0001

Data Index: 1014776 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3298. Min Act: -0.0000

Data Index: 558308 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1891194 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1054334 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1646656 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1649831 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1931428 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.0449. Min Act: -0.0000

Data Index: 509575 (The Pile)

Max Activating Token Index: 788