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

Dataset: The Pile

Neuron 1800 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8724. Min Act: -0.0000

Data Index: 229083 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1086696 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7285. Min Act: -0.0000

Data Index: 509625 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7663. Min Act: -0.0000

Data Index: 434021 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1809614 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1436896 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6904. Min Act: -0.0000

Data Index: 64015 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1126389 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1457283 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1203910 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6558. Min Act: -0.0000

Data Index: 563983 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1009255 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1177039 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6440. Min Act: -0.0000

Data Index: 576351 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6527. Min Act: -0.0000

Data Index: 595167 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1103873 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1225718 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6407. Min Act: -0.0000

Data Index: 105585 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6323. Min Act: -0.0000

Data Index: 918554 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1551560 (The Pile)

Max Activating Token Index: 855