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

Dataset: The Pile

Neuron 3281 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6333. Min Range: -4.6333

Max Act: 4.6333. Min Act: -0.0000

Data Index: 113351 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 4.6333. Min Range: -4.6333

Max Act: 4.1853. Min Act: -0.0000

Data Index: 1984625 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.7878. Min Act: -0.0000

Data Index: 1916962 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.7653. Min Act: -0.0000

Data Index: 553542 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.5437. Min Act: -0.0000

Data Index: 305821 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.6725. Min Act: -0.0000

Data Index: 343170 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.5533. Min Act: -0.0000

Data Index: 1918173 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.5672. Min Act: -0.0000

Data Index: 1502741 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.5986. Min Act: -0.0000

Data Index: 245042 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.3712. Min Act: -0.0000

Data Index: 975882 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.2010. Min Act: -0.0000

Data Index: 369723 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.5101. Min Act: -0.0000

Data Index: 1638405 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.2030. Min Act: -0.0000

Data Index: 253857 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.0723. Min Act: -0.0000

Data Index: 1900625 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.4121. Min Act: -0.0000

Data Index: 411124 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.2301. Min Act: -0.0000

Data Index: 1304485 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.2169. Min Act: -0.0000

Data Index: 532876 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 4.6333. Min Range: -4.6333

Max Act: 2.8507. Min Act: -0.0000

Data Index: 603908 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.1604. Min Act: -0.0000

Data Index: 1962951 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 4.6333. Min Range: -4.6333

Max Act: 3.5329. Min Act: -0.0000

Data Index: 133309 (The Pile)

Max Activating Token Index: 472