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

Dataset: The Pile

Neuron 4776 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.9274. Min Act: -0.0000

Data Index: 288500 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1310240 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8911. Min Act: -0.0000

Data Index: 586178 (The Pile)

Max Activating Token Index: 865

Text #3

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1694077 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1190416 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1542374 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1749449 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1955064 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1978082 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7757. Min Act: -0.0000

Data Index: 757442 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1785809 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8573. Min Act: -0.0000

Data Index: 302575 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8179. Min Act: -0.0000

Data Index: 806194 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1475156 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7846. Min Act: -0.0000

Data Index: 107079 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7734. Min Act: -0.0000

Data Index: 201036 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1349492 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1810363 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1219230 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.6809. Min Act: -0.0000

Data Index: 484975 (The Pile)

Max Activating Token Index: 737