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

Dataset: The Pile

Neuron 1840 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1608844 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1806519 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1047094 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1810341 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1556432 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1750173 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8415. Min Act: -0.0000

Data Index: 43820 (The Pile)

Max Activating Token Index: 471

Text #7

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1713520 (The Pile)

Max Activating Token Index: 476

Text #8

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8171. Min Act: -0.0000

Data Index: 887895 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1005853 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7777. Min Act: 0.0000

Data Index: 918826 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7596. Min Act: -0.0000

Data Index: 834941 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1034292 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7955. Min Act: -0.0000

Data Index: 483598 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7241. Min Act: -0.0000

Data Index: 20003 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1128913 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7660. Min Act: -0.0000

Data Index: 522562 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7037. Min Act: -0.0000

Data Index: 6644 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7025. Min Act: -0.0000

Data Index: 719171 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7215. Min Act: -0.0000

Data Index: 879721 (The Pile)

Max Activating Token Index: 427