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

Dataset: The Pile

Neuron 3147 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: 1.8082. Min Range: -1.8082

Max Act: 1.8082. Min Act: -0.0000

Data Index: 1904175 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1214781 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.3227. Min Act: -0.0000

Data Index: 497055 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.3489. Min Act: -0.0000

Data Index: 781662 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1872543 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.6306. Min Act: -0.0000

Data Index: 1086226 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.4582. Min Act: -0.0000

Data Index: 809216 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2794. Min Act: -0.0000

Data Index: 467328 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1814292 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1813. Min Act: -0.0000

Data Index: 655765 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1294724 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1814736 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1944. Min Act: -0.0000

Data Index: 71577 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1774090 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1827574 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1760072 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 1.8082. Min Range: -1.8082

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1795109 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1109. Min Act: -0.0000

Data Index: 407697 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.0144. Min Act: -0.0000

Data Index: 584962 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 1.8082. Min Range: -1.8082

Max Act: 0.8727. Min Act: -0.0000

Data Index: 573595 (The Pile)

Max Activating Token Index: 891