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

Dataset: The Pile

Neuron 81 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0393. Min Range: -3.0393

Max Act: 3.0393. Min Act: -0.0000

Data Index: 955310 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.3379. Min Act: -0.0000

Data Index: 640686 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.5787. Min Act: -0.0000

Data Index: 1037230 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.4251. Min Act: -0.0000

Data Index: 1311726 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.4312. Min Act: -0.0000

Data Index: 1728536 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.0917. Min Act: -0.0000

Data Index: 493252 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.0162. Min Act: -0.0000

Data Index: 1136156 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.2468. Min Act: -0.0000

Data Index: 1651634 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.1324. Min Act: -0.0000

Data Index: 1475539 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 3.0393. Min Range: -3.0393

Max Act: 1.9641. Min Act: -0.0000

Data Index: 50361 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.0555. Min Act: -0.0000

Data Index: 1589611 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.1235. Min Act: -0.0000

Data Index: 1508579 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.5085. Min Act: -0.0000

Data Index: 549976 (The Pile)

Max Activating Token Index: 920

Text #13

Max Range: 3.0393. Min Range: -3.0393

Max Act: 1.9791. Min Act: -0.0000

Data Index: 863385 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 3.0393. Min Range: -3.0393

Max Act: 1.9814. Min Act: -0.0000

Data Index: 462871 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 3.0393. Min Range: -3.0393

Max Act: 1.8791. Min Act: -0.0000

Data Index: 130941 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.0861. Min Act: -0.0000

Data Index: 50033 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.0668. Min Act: -0.0000

Data Index: 669238 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.0766. Min Act: -0.0000

Data Index: 671410 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 3.0393. Min Range: -3.0393

Max Act: 2.0662. Min Act: -0.0000

Data Index: 245903 (The Pile)

Max Activating Token Index: 195