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

Dataset: The Pile

Neuron 971 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0676. Min Range: -1.0676

Max Act: 1.0676. Min Act: -0.0000

Data Index: 200628 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.6009. Min Act: -0.0000

Data Index: 908131 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5712. Min Act: -0.0000

Data Index: 741267 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1588656 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5717. Min Act: -0.0000

Data Index: 584936 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5405. Min Act: -0.0000

Data Index: 61886 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5720. Min Act: -0.0000

Data Index: 338742 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5933. Min Act: -0.0000

Data Index: 557490 (The Pile)

Max Activating Token Index: 458

Text #8

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1448171 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5370. Min Act: -0.0000

Data Index: 210692 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1873210 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5421. Min Act: -0.0000

Data Index: 722786 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5443. Min Act: -0.0000

Data Index: 659676 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5406. Min Act: -0.0000

Data Index: 734927 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5363. Min Act: -0.0000

Data Index: 526233 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1968022 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.4955. Min Act: -0.0000

Data Index: 476293 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1336076 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.5072. Min Act: -0.0000

Data Index: 283241 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 1.0676. Min Range: -1.0676

Max Act: 0.4750. Min Act: -0.0000

Data Index: 347187 (The Pile)

Max Activating Token Index: 909