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

Dataset: The Pile

Neuron 3213 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: 1.2372. Min Range: -1.2372

Max Act: 1.2372. Min Act: -0.0000

Data Index: 255490 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1008184 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1225801 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1350667 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1420180 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1454889 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1443988 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1486499 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1931399 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1021191 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1244036 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7873. Min Act: -0.0000

Data Index: 385901 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7662. Min Act: -0.0000

Data Index: 740299 (The Pile)

Max Activating Token Index: 666

Text #13

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1633588 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7610. Min Act: -0.0001

Data Index: 349180 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1894589 (The Pile)

Max Activating Token Index: 384

Text #16

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1341949 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.7222. Min Act: -0.0000

Data Index: 957314 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1131275 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1782838 (The Pile)

Max Activating Token Index: 627