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

Dataset: The Pile

Neuron 4395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.3549. Min Act: -0.0000

Data Index: 433747 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.3368. Min Act: -0.0000

Data Index: 285573 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1348537 (The Pile)

Max Activating Token Index: 1017

Text #3

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.3885. Min Act: -0.0000

Data Index: 178396 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.3466. Min Act: -0.0000

Data Index: 570299 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1849275 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.2634. Min Act: -0.0000

Data Index: 876041 (The Pile)

Max Activating Token Index: 747

Text #7

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1877580 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1799725 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1611227 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1073657 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1341729 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1552. Min Act: -0.0000

Data Index: 438321 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1008694 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1213. Min Act: -0.0000

Data Index: 879900 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.0166. Min Act: -0.0000

Data Index: 607356 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1715767 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1997048 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 1.3885. Min Range: -1.3885

Max Act: 1.0964. Min Act: -0.0000

Data Index: 704666 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 1.3885. Min Range: -1.3885

Max Act: 0.9675. Min Act: -0.0000

Data Index: 690601 (The Pile)

Max Activating Token Index: 653