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

Dataset: The Pile

Neuron 1254 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: 0.7589. Min Range: -0.7589

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1973285 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1063597 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1352439 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1898782 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1519460 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7322. Min Act: -0.0000

Data Index: 794708 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1822488 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1997920 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1422017 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6289. Min Act: -0.0000

Data Index: 411769 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6716. Min Act: -0.0000

Data Index: 333713 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1725547 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1983159 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1007512 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5603. Min Act: -0.0000

Data Index: 337054 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1166674 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6367. Min Act: -0.0000

Data Index: 305162 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6114. Min Act: -0.0000

Data Index: 351259 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1192259 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1466521 (The Pile)

Max Activating Token Index: 637