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

Dataset: The Pile

Neuron 3821 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5403. Min Act: -0.0000

Data Index: 641535 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4696. Min Act: -0.0000

Data Index: 847375 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1615389 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1625087 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3533. Min Act: 0.0000

Data Index: 867882 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3674. Min Act: 0.0000

Data Index: 1024541 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1762877 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3407. Min Act: -0.0000

Data Index: 225408 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3490. Min Act: -0.0000

Data Index: 789079 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1423677 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3669. Min Act: -0.0000

Data Index: 203364 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3539. Min Act: -0.0000

Data Index: 671649 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3120. Min Act: -0.0000

Data Index: 412141 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3421. Min Act: -0.0000

Data Index: 122145 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1375910 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.2824. Min Act: -0.0000

Data Index: 856491 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1248915 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3048. Min Act: -0.0000

Data Index: 970763 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1038913 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3146. Min Act: -0.0000

Data Index: 753659 (The Pile)

Max Activating Token Index: 1001