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

Dataset: The Pile

Neuron 1500 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8373. Min Act: -0.0000

Data Index: 774419 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1198683 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1712491 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1649327 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1930361 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1065329 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6921. Min Act: -0.0000

Data Index: 330399 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1268837 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1227367 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6003. Min Act: -0.0000

Data Index: 212443 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6166. Min Act: -0.0000

Data Index: 381 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1870043 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6098. Min Act: -0.0000

Data Index: 92750 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1830564 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6012. Min Act: -0.0000

Data Index: 280255 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6058. Min Act: -0.0000

Data Index: 2102 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6124. Min Act: -0.0000

Data Index: 866726 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1157852 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6202. Min Act: -0.0000

Data Index: 808954 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.6365. Min Act: -0.0000

Data Index: 88708 (The Pile)

Max Activating Token Index: 1023