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

Dataset: The Pile

Neuron 4214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7545. Min Act: -0.0000

Data Index: 322876 (The Pile)

Max Activating Token Index: 77

Text #1

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7254. Min Act: -0.0000

Data Index: 161637 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7412. Min Act: -0.0000

Data Index: 738951 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1183366 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6430. Min Act: -0.0000

Data Index: 699957 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1187429 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5503. Min Act: -0.0000

Data Index: 682188 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5351. Min Act: -0.0000

Data Index: 708862 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1352606 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1428795 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4923. Min Act: -0.0000

Data Index: 966419 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4678. Min Act: -0.0000

Data Index: 218635 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1381861 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4750. Min Act: -0.0000

Data Index: 63484 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1719397 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4308. Min Act: -0.0000

Data Index: 174864 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1105406 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4605. Min Act: -0.0000

Data Index: 708927 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4561. Min Act: -0.0000

Data Index: 112399 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1966942 (The Pile)

Max Activating Token Index: 726