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

Dataset: The Pile

Neuron 2692 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: 0.9267. Min Range: -0.9267

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1135068 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8605. Min Act: -0.0000

Data Index: 381719 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1531065 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1934014 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1629096 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9267. Min Act: -0.0000

Data Index: 57331 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1519303 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1729581 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.9048. Min Act: -0.0000

Data Index: 898624 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1016673 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1911587 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1426639 (The Pile)

Max Activating Token Index: 898

Text #12

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1601598 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7825. Min Act: -0.0000

Data Index: 151616 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1080080 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1743286 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1328658 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7128. Min Act: -0.0000

Data Index: 32685 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7206. Min Act: -0.0000

Data Index: 569112 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.9267. Min Range: -0.9267

Max Act: 0.7270. Min Act: -0.0000

Data Index: 387102 (The Pile)

Max Activating Token Index: 37