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

Dataset: The Pile

Neuron 1004 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: 1.1769. Min Range: -1.1769

Max Act: 1.1769. Min Act: -0.0000

Data Index: 1180368 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7736. Min Act: -0.0000

Data Index: 370090 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7736. Min Act: -0.0000

Data Index: 823908 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1139772 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1432970 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1632357 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7080. Min Act: -0.0000

Data Index: 184985 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1489354 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6582. Min Act: -0.0000

Data Index: 43031 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6255. Min Act: -0.0000

Data Index: 735015 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.5965. Min Act: -0.0000

Data Index: 361582 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.5814. Min Act: -0.0000

Data Index: 333134 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6184. Min Act: -0.0000

Data Index: 826309 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6302. Min Act: -0.0000

Data Index: 837511 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1185366 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1877997 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1903839 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.5772. Min Act: -0.0000

Data Index: 807722 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6134. Min Act: -0.0001

Data Index: 981535 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.5313. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 720