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

Dataset: The Pile

Neuron 497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0451. Min Range: -1.0451

Max Act: 1.0451. Min Act: -0.0000

Data Index: 690066 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1078252 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.8590. Min Act: -0.0000

Data Index: 340956 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1237313 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7003. Min Act: -0.0000

Data Index: 430011 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6925. Min Act: -0.0000

Data Index: 512584 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6643. Min Act: -0.0000

Data Index: 47823 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6890. Min Act: -0.0000

Data Index: 523629 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1080254 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6405. Min Act: -0.0000

Data Index: 266866 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1269099 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1652764 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6988. Min Act: -0.0000

Data Index: 446239 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1371633 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6234. Min Act: -0.0000

Data Index: 730225 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6503. Min Act: -0.0000

Data Index: 716334 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1321805 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6703. Min Act: -0.0000

Data Index: 848210 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1917540 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 1.0451. Min Range: -1.0451

Max Act: 0.6568. Min Act: -0.0000

Data Index: 733951 (The Pile)

Max Activating Token Index: 706