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

Dataset: The Pile

Neuron 492 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: 0.5180. Min Range: -0.5180

Max Act: 0.5180. Min Act: -0.0000

Data Index: 945316 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4275. Min Act: -0.0000

Data Index: 443640 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.4156. Min Act: -0.0000

Data Index: 206032 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1044294 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2708. Min Act: -0.0000

Data Index: 120779 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1075133 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1003552 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2903. Min Act: -0.0000

Data Index: 561239 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1781126 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2858. Min Act: -0.0000

Data Index: 198355 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2771. Min Act: -0.0000

Data Index: 729601 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1409429 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1476339 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1535937 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1979272 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2702. Min Act: -0.0000

Data Index: 675780 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2394. Min Act: -0.0000

Data Index: 700731 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1333030 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2635. Min Act: -0.0000

Data Index: 775161 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 0.5180. Min Range: -0.5180

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1237423 (The Pile)

Max Activating Token Index: 878