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

Dataset: The Pile

Neuron 527 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.7133. Min Act: -0.0000

Data Index: 221227 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.4752. Min Act: -0.0000

Data Index: 380823 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.4861. Min Act: -0.0000

Data Index: 586944 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.9697. Min Act: -0.0000

Data Index: 1238315 (The Pile)

Max Activating Token Index: 327

Text #4

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.0025. Min Act: -0.0000

Data Index: 143032 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.0351. Min Act: -0.0000

Data Index: 1216924 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.8306. Min Act: -0.0000

Data Index: 1848018 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.6341. Min Act: -0.0000

Data Index: 1557251 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.0046. Min Act: -0.0000

Data Index: 1073223 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.7607. Min Act: -0.0000

Data Index: 1605740 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.4743. Min Act: -0.0000

Data Index: 774142 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.1608. Min Act: -0.0000

Data Index: 1960658 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.8386. Min Act: -0.0000

Data Index: 1241999 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 5.7133. Min Range: -5.7133

Max Act: 5.0398. Min Act: -0.0000

Data Index: 513515 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.2611. Min Act: -0.0000

Data Index: 1958886 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.4696. Min Act: -0.0000

Data Index: 1406502 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.3504. Min Act: -0.0000

Data Index: 540718 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.3613. Min Act: -0.0000

Data Index: 1913144 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.3049. Min Act: -0.0000

Data Index: 1133275 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 5.7133. Min Range: -5.7133

Max Act: 4.3364. Min Act: -0.0000

Data Index: 484166 (The Pile)

Max Activating Token Index: 895