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

Dataset: The Pile

Neuron 3410 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1415. Min Range: -1.1415

Max Act: 1.1415. Min Act: -0.0000

Data Index: 811334 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 1.1415. Min Range: -1.1415

Max Act: 1.0408. Min Act: -0.0000

Data Index: 879377 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1096793 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 1.1415. Min Range: -1.1415

Max Act: 1.0906. Min Act: -0.0000

Data Index: 221717 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 1.1415. Min Range: -1.1415

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1063162 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.9947. Min Act: -0.0000

Data Index: 354999 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.9515. Min Act: -0.0000

Data Index: 886054 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 1.1415. Min Range: -1.1415

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1184041 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8423. Min Act: -0.0000

Data Index: 508759 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1193714 (The Pile)

Max Activating Token Index: 995

Text #10

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8435. Min Act: -0.0000

Data Index: 647649 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1892363 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8801. Min Act: -0.0000

Data Index: 672082 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8908. Min Act: -0.0000

Data Index: 835658 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1125132 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8279. Min Act: -0.0000

Data Index: 896085 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.7813. Min Act: 0.0000

Data Index: 1955581 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1545238 (The Pile)

Max Activating Token Index: 836

Text #18

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8308. Min Act: -0.0000

Data Index: 775771 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 1.1415. Min Range: -1.1415

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1488239 (The Pile)

Max Activating Token Index: 860