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

Dataset: The Pile

Neuron 2910 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1494755 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1868698 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1316532 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1662023 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1674178 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7032. Min Act: -0.0000

Data Index: 753948 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7205. Min Act: -0.0000

Data Index: 499348 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1759751 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1993686 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1683581 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1437304 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7297. Min Act: -0.0000

Data Index: 458563 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7208. Min Act: -0.0000

Data Index: 959845 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1068034 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1044627 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1014997 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7159. Min Act: -0.0000

Data Index: 208346 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1554549 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1446972 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 0.7753. Min Range: -0.7753

Max Act: 0.6965. Min Act: -0.0000

Data Index: 559446 (The Pile)

Max Activating Token Index: 609