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

Dataset: The Pile

Neuron 4708 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1125462 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2811. Min Act: -0.0000

Data Index: 782192 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1394320 (The Pile)

Max Activating Token Index: 200

Text #3

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1448984 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1718965 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2228. Min Act: -0.0000

Data Index: 168722 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1535600 (The Pile)

Max Activating Token Index: 57

Text #7

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1916945 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1535661 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2261. Min Act: -0.0000

Data Index: 44909 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2251. Min Act: -0.0000

Data Index: 241145 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1828689 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2192. Min Act: -0.0000

Data Index: 468521 (The Pile)

Max Activating Token Index: 995

Text #13

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1943. Min Act: -0.0000

Data Index: 302408 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1710480 (The Pile)

Max Activating Token Index: 509

Text #15

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1730434 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1066497 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1861. Min Act: -0.0000

Data Index: 640128 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1951. Min Act: -0.0000

Data Index: 515560 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1638105 (The Pile)

Max Activating Token Index: 607