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

Dataset: The Pile

Neuron 2610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1631066 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.8270. Min Act: -0.0000

Data Index: 170359 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1594361 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1078438 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6554. Min Act: -0.0000

Data Index: 166679 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7173. Min Act: -0.0000

Data Index: 477093 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6245. Min Act: -0.0000

Data Index: 909283 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1185166 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5900. Min Act: -0.0000

Data Index: 555293 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.7152. Min Act: -0.0000

Data Index: 634126 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6530. Min Act: -0.0000

Data Index: 60938 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1601760 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5582. Min Act: -0.0000

Data Index: 839625 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6619. Min Act: 0.0000

Data Index: 1075473 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6389. Min Act: -0.0000

Data Index: 58788 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6532. Min Act: -0.0000

Data Index: 868228 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1170034 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1940491 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.5492. Min Act: -0.0000

Data Index: 393418 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.8323. Min Range: -0.8323

Max Act: 0.6202. Min Act: -0.0000

Data Index: 535022 (The Pile)

Max Activating Token Index: 290