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

Dataset: The Pile

Neuron 3750 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: 3.4954. Min Range: -3.4954

Max Act: 3.4954. Min Act: -0.0000

Data Index: 228460 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3581. Min Act: -0.0000

Data Index: 138516 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4326. Min Act: -0.0000

Data Index: 84408 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.6230. Min Act: -0.0000

Data Index: 1841970 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3198. Min Act: -0.0000

Data Index: 1898667 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3468. Min Act: -0.0000

Data Index: 1148530 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.7090. Min Act: -0.0000

Data Index: 907531 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.2202. Min Act: -0.0000

Data Index: 1655832 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.9865. Min Act: -0.0000

Data Index: 1743908 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.2454. Min Act: -0.0000

Data Index: 1011424 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.8507. Min Act: -0.0000

Data Index: 1215571 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1314408 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.0825. Min Act: -0.0000

Data Index: 1373907 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.3629. Min Act: -0.0000

Data Index: 254193 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.4842. Min Act: -0.0000

Data Index: 210584 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.3707. Min Act: -0.0000

Data Index: 700533 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.8124. Min Act: -0.0000

Data Index: 684372 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.7221. Min Act: -0.0000

Data Index: 517062 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.6495. Min Act: -0.0000

Data Index: 955074 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 3.4954. Min Range: -3.4954

Max Act: 2.6536. Min Act: -0.0000

Data Index: 1533149 (The Pile)

Max Activating Token Index: 839