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

Dataset: The Pile

Neuron 3094 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: 1.0257. Min Range: -1.0257

Max Act: 0.8828. Min Act: -0.0000

Data Index: 122978 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.0257. Min Range: -1.0257

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1185146 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1886753 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7932. Min Act: -0.0000

Data Index: 188585 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8431. Min Act: -0.0000

Data Index: 787357 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7462. Min Act: -0.0000

Data Index: 923870 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1202387 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1981421 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7998. Min Act: -0.0000

Data Index: 681961 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7072. Min Act: -0.0000

Data Index: 172737 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7204. Min Act: -0.0000

Data Index: 557245 (The Pile)

Max Activating Token Index: 226

Text #11

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1457596 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1366645 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8028. Min Act: -0.0000

Data Index: 341431 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1973360 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.6402. Min Act: -0.0000

Data Index: 743219 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.6274. Min Act: -0.0000

Data Index: 127609 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.6640. Min Act: -0.0000

Data Index: 602884 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7207. Min Act: -0.0000

Data Index: 849093 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.6222. Min Act: -0.0000

Data Index: 946699 (The Pile)

Max Activating Token Index: 738