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

Dataset: The Pile

Neuron 3424 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: 0.9778. Min Range: -0.9778

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1765988 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.9778. Min Act: -0.0000

Data Index: 601403 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.8895. Min Act: -0.0000

Data Index: 161917 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1259898 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7876. Min Act: 0.0000

Data Index: 349025 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1721147 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7661. Min Act: 0.0000

Data Index: 1758735 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7118. Min Act: -0.0000

Data Index: 119783 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7087. Min Act: -0.0000

Data Index: 648547 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7316. Min Act: 0.0000

Data Index: 602631 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7172. Min Act: -0.0000

Data Index: 941867 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7068. Min Act: -0.0000

Data Index: 488504 (The Pile)

Max Activating Token Index: 232

Text #12

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1392778 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1810691 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.6609. Min Act: -0.0000

Data Index: 513928 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1276750 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1638047 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.6935. Min Act: -0.0000

Data Index: 96236 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1010176 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.9778. Min Range: -0.9778

Max Act: 0.6815. Min Act: -0.0000

Data Index: 359709 (The Pile)

Max Activating Token Index: 702