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

Dataset: The Pile

Neuron 3730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.1158. Min Act: -0.0000

Data Index: 615573 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.2366. Min Act: -0.0000

Data Index: 1400671 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1047418 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1163470 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1048702 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1837874 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0209. Min Act: -0.0000

Data Index: 910122 (The Pile)

Max Activating Token Index: 880

Text #7

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0063. Min Act: -0.0000

Data Index: 562471 (The Pile)

Max Activating Token Index: 777

Text #8

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1655655 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1431370 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0812. Min Act: -0.0000

Data Index: 386204 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.7752. Min Act: -0.0000

Data Index: 86833 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1232947 (The Pile)

Max Activating Token Index: 170

Text #13

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1940653 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1379248 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0669. Min Act: -0.0000

Data Index: 692984 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 1.2504. Min Range: -1.2504

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1860155 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1146712 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1326796 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 1.2504. Min Range: -1.2504

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1564807 (The Pile)

Max Activating Token Index: 932