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

Dataset: The Pile

Neuron 3108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.5568. Min Act: -0.0000

Data Index: 505111 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.5960. Min Act: -0.0000

Data Index: 140237 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1411770 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1012961 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1345574 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 1.5960. Min Range: -1.5960

Max Act: 1.0018. Min Act: -0.0000

Data Index: 852640 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9315. Min Act: -0.0000

Data Index: 596176 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9000. Min Act: -0.0000

Data Index: 984466 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1318545 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8660. Min Act: -0.0000

Data Index: 792588 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1279235 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1577817 (The Pile)

Max Activating Token Index: 330

Text #12

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1447602 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1272056 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.9269. Min Act: -0.0000

Data Index: 828318 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1249617 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1876191 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1361487 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.7731. Min Act: -0.0000

Data Index: 188215 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 1.5960. Min Range: -1.5960

Max Act: 0.8206. Min Act: -0.0000

Data Index: 539524 (The Pile)

Max Activating Token Index: 821