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

Dataset: The Pile

Neuron 953 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: 1.9449. Min Range: -1.9449

Max Act: 1.9358. Min Act: -0.0000

Data Index: 1131042 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.9449. Min Act: -0.0000

Data Index: 922974 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.6848. Min Act: -0.0000

Data Index: 272747 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.8558. Min Act: -0.0000

Data Index: 1882849 (The Pile)

Max Activating Token Index: 600

Text #4

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.5210. Min Act: -0.0000

Data Index: 282401 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.7223. Min Act: -0.0000

Data Index: 527991 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.6215. Min Act: -0.0000

Data Index: 195181 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.5767. Min Act: -0.0000

Data Index: 1933984 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.6677. Min Act: -0.0000

Data Index: 713780 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.5372. Min Act: -0.0000

Data Index: 302154 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.5730. Min Act: -0.0000

Data Index: 462334 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.6717. Min Act: -0.0000

Data Index: 1483709 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.4920. Min Act: -0.0000

Data Index: 1170765 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1483013 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.6514. Min Act: -0.0000

Data Index: 380309 (The Pile)

Max Activating Token Index: 874

Text #15

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.6805. Min Act: -0.0000

Data Index: 1310313 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.5033. Min Act: -0.0000

Data Index: 876958 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.4952. Min Act: -0.0000

Data Index: 321037 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.5372. Min Act: -0.0000

Data Index: 779499 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.9449. Min Range: -1.9449

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1873284 (The Pile)

Max Activating Token Index: 861