Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1968 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.9101. Min Act: -0.0000

Data Index: 177940 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.4862. Min Act: -0.0000

Data Index: 60689 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.4885. Min Act: -0.0000

Data Index: 1000462 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3236. Min Act: -0.0000

Data Index: 658718 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1245122 (The Pile)

Max Activating Token Index: 8

Text #5

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.2081. Min Act: -0.0000

Data Index: 1774447 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1568. Min Act: -0.0000

Data Index: 1104880 (The Pile)

Max Activating Token Index: 17

Text #7

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1842765 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.2433. Min Act: -0.0000

Data Index: 878597 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1800. Min Act: -0.0000

Data Index: 88284 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1166. Min Act: -0.0000

Data Index: 149872 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1203. Min Act: -0.0000

Data Index: 934311 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1959. Min Act: -0.0000

Data Index: 543688 (The Pile)

Max Activating Token Index: 16

Text #13

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1186362 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1895491 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1094. Min Act: -0.0000

Data Index: 583295 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.1089. Min Act: -0.0000

Data Index: 506989 (The Pile)

Max Activating Token Index: 21

Text #17

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.0784. Min Act: -0.0000

Data Index: 330707 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1230583 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1137195 (The Pile)

Max Activating Token Index: 14