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

Dataset: The Pile

Neuron 2359 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5940. Min Range: -5.5940

Max Act: 5.5036. Min Act: -0.0000

Data Index: 1952173 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 5.5940. Min Range: -5.5940

Max Act: 5.4748. Min Act: -0.0000

Data Index: 715549 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 5.5940. Min Range: -5.5940

Max Act: 5.3192. Min Act: -0.0000

Data Index: 387113 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.9326. Min Act: -0.0000

Data Index: 1930781 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 5.5940. Min Range: -5.5940

Max Act: 5.5940. Min Act: -0.0000

Data Index: 1724518 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 5.5940. Min Range: -5.5940

Max Act: 5.0024. Min Act: -0.0000

Data Index: 352102 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 5.5940. Min Range: -5.5940

Max Act: 5.1851. Min Act: -0.0000

Data Index: 60180 (The Pile)

Max Activating Token Index: 588

Text #7

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.9886. Min Act: -0.0000

Data Index: 1658472 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.9847. Min Act: -0.0000

Data Index: 204755 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 5.5940. Min Range: -5.5940

Max Act: 5.1063. Min Act: -0.0000

Data Index: 1246522 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.7984. Min Act: -0.0000

Data Index: 182522 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.7591. Min Act: -0.0000

Data Index: 1002072 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.9287. Min Act: -0.0000

Data Index: 182575 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.7247. Min Act: -0.0000

Data Index: 1160843 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.4818. Min Act: -0.0000

Data Index: 442844 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.4481. Min Act: -0.0000

Data Index: 962879 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.4831. Min Act: -0.0000

Data Index: 1532192 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.6102. Min Act: -0.0000

Data Index: 1250041 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.4362. Min Act: -0.0000

Data Index: 1958239 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 5.5940. Min Range: -5.5940

Max Act: 4.2504. Min Act: -0.0000

Data Index: 90536 (The Pile)

Max Activating Token Index: 23