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

Dataset: The Pile

Neuron 2286 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1308536 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1637623 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1338929 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6284. Min Act: -0.0000

Data Index: 123043 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6320. Min Act: -0.0000

Data Index: 559318 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6028. Min Act: -0.0000

Data Index: 416286 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6322. Min Act: -0.0000

Data Index: 279875 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6519. Min Act: -0.0000

Data Index: 190787 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1076219 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5990. Min Act: -0.0000

Data Index: 98863 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5940. Min Act: -0.0000

Data Index: 308781 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1744037 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5731. Min Act: -0.0000

Data Index: 252070 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5470. Min Act: -0.0000

Data Index: 975561 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1498894 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1685504 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1729489 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1243742 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1263182 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 0.8713. Min Range: -0.8713

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1618537 (The Pile)

Max Activating Token Index: 772