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

Dataset: The Pile

Neuron 3567 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1406562 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6727. Min Act: -0.0000

Data Index: 967564 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5930. Min Act: -0.0000

Data Index: 357943 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5707. Min Act: -0.0000

Data Index: 754297 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1213459 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1927523 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1447384 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1293226 (The Pile)

Max Activating Token Index: 933

Text #8

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1917965 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4907. Min Act: -0.0000

Data Index: 237231 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1660181 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1389898 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5330. Min Act: -0.0000

Data Index: 451686 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5007. Min Act: -0.0000

Data Index: 246942 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1060927 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1569712 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1275891 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4567. Min Act: -0.0000

Data Index: 418267 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1211177 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4774. Min Act: 0.0000

Data Index: 288683 (The Pile)

Max Activating Token Index: 657