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

Dataset: The Pile

Neuron 2734 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: 0.7111. Min Range: -0.7111

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1072972 (The Pile)

Max Activating Token Index: 986

Text #1

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1381300 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1077092 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6469. Min Act: -0.0000

Data Index: 395090 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5469. Min Act: -0.0000

Data Index: 642389 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1943645 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4651. Min Act: -0.0000

Data Index: 935921 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4372. Min Act: -0.0000

Data Index: 382593 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4685. Min Act: -0.0000

Data Index: 710070 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4769. Min Act: -0.0000

Data Index: 782443 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4937. Min Act: -0.0000

Data Index: 766292 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1542689 (The Pile)

Max Activating Token Index: 431

Text #12

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4367. Min Act: -0.0000

Data Index: 711361 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.3716. Min Act: -0.0000

Data Index: 475038 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.3625. Min Act: -0.0000

Data Index: 949957 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.3453. Min Act: -0.0000

Data Index: 750057 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1150877 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.3481. Min Act: -0.0000

Data Index: 862687 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.3836. Min Act: 0.0000

Data Index: 1572717 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.3785. Min Act: -0.0000

Data Index: 743350 (The Pile)

Max Activating Token Index: 406