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

Dataset: The Pile

Neuron 721 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: 1.0907. Min Range: -1.0907

Max Act: 1.0907. Min Act: -0.0000

Data Index: 911340 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1132406 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1437783 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1370816 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1632261 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8431. Min Act: -0.0000

Data Index: 930001 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1624951 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8081. Min Act: -0.0000

Data Index: 31518 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1906917 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7774. Min Act: -0.0000

Data Index: 746705 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7350. Min Act: -0.0000

Data Index: 445412 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1002001 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7514. Min Act: -0.0000

Data Index: 990538 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.7738. Min Act: -0.0000

Data Index: 693173 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.6559. Min Act: -0.0000

Data Index: 498548 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1111212 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1238853 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.6929. Min Act: -0.0000

Data Index: 111236 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.6613. Min Act: -0.0000

Data Index: 936614 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.0907. Min Range: -1.0907

Max Act: 0.6661. Min Act: -0.0000

Data Index: 1174328 (The Pile)

Max Activating Token Index: 301