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

Dataset: The Pile

Neuron 3969 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: 0.5717. Min Range: -0.5717

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1119879 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5625. Min Act: -0.0000

Data Index: 595223 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5426. Min Act: -0.0000

Data Index: 758063 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5717. Min Act: -0.0000

Data Index: 319790 (The Pile)

Max Activating Token Index: 526

Text #4

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1522931 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1949946 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5356. Min Act: -0.0000

Data Index: 699029 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1474043 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5067. Min Act: -0.0000

Data Index: 45420 (The Pile)

Max Activating Token Index: 688

Text #9

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1840164 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4911. Min Act: -0.0000

Data Index: 454537 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1189609 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1391704 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1504311 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1682628 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4802. Min Act: -0.0000

Data Index: 776295 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4943. Min Act: -0.0000

Data Index: 952346 (The Pile)

Max Activating Token Index: 379

Text #17

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4772. Min Act: -0.0000

Data Index: 3709 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4782. Min Act: -0.0000

Data Index: 688230 (The Pile)

Max Activating Token Index: 919

Text #19

Max Range: 0.5717. Min Range: -0.5717

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1861837 (The Pile)

Max Activating Token Index: 584