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

Dataset: The Pile

Neuron 3356 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: 1.0616. Min Range: -1.0616

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1687939 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9863. Min Act: -0.0000

Data Index: 646875 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1504334 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 1.0616. Min Range: -1.0616

Max Act: 1.0230. Min Act: -0.0000

Data Index: 76534 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1868605 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9101. Min Act: -0.0000

Data Index: 235739 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8833. Min Act: -0.0000

Data Index: 1286439 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1696253 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8757. Min Act: -0.0000

Data Index: 899069 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8939. Min Act: -0.0000

Data Index: 16512 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8603. Min Act: -0.0000

Data Index: 209029 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1832078 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8399. Min Act: -0.0000

Data Index: 965375 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1855590 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1531056 (The Pile)

Max Activating Token Index: 559

Text #15

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8471. Min Act: -0.0000

Data Index: 308395 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1333158 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8392. Min Act: -0.0000

Data Index: 477904 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8878. Min Act: -0.0000

Data Index: 638996 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 1.0616. Min Range: -1.0616

Max Act: 0.8314. Min Act: -0.0000

Data Index: 254470 (The Pile)

Max Activating Token Index: 1023