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

Dataset: The Pile

Neuron 1715 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.6953. Min Act: -0.0000

Data Index: 334717 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.5860. Min Act: -0.0000

Data Index: 317969 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4109. Min Act: -0.0000

Data Index: 1236225 (The Pile)

Max Activating Token Index: 273

Text #3

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.4483. Min Act: -0.0000

Data Index: 170675 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1017241 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1883551 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1077640 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1113377 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1963126 (The Pile)

Max Activating Token Index: 99

Text #9

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1295049 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1828. Min Act: -0.0000

Data Index: 629710 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1926239 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1244529 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.0991. Min Act: -0.0000

Data Index: 692416 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1195865 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1779956 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1793367 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.0128. Min Act: -0.0000

Data Index: 1082363 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1158107 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.6953. Min Range: -1.6953

Max Act: 1.1013. Min Act: -0.0000

Data Index: 264480 (The Pile)

Max Activating Token Index: 664