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

Dataset: The Pile

Neuron 3331 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: 0.8073. Min Range: -0.8073

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1014866 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1989321 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1735893 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1277044 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1075798 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5256. Min Act: -0.0000

Data Index: 596311 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1220793 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1558518 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4826. Min Act: -0.0000

Data Index: 781305 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1511081 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4834. Min Act: -0.0000

Data Index: 121875 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1259943 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4412. Min Act: -0.0000

Data Index: 418422 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1301960 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4149. Min Act: -0.0000

Data Index: 471906 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1686176 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1439628 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4371. Min Act: -0.0000

Data Index: 499734 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4131. Min Act: -0.0000

Data Index: 143617 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.4173. Min Act: -0.0000

Data Index: 902181 (The Pile)

Max Activating Token Index: 909