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

Dataset: The Pile

Neuron 2539 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: 0.8569. Min Range: -0.8569

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1351561 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.8569. Min Act: -0.0000

Data Index: 199275 (The Pile)

Max Activating Token Index: 10

Text #2

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7643. Min Act: -0.0000

Data Index: 661526 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1079685 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1853028 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1280871 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6447. Min Act: -0.0000

Data Index: 798016 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1488949 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1177233 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6434. Min Act: -0.0000

Data Index: 733693 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1926046 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5809. Min Act: -0.0000

Data Index: 826496 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6204. Min Act: -0.0000

Data Index: 577703 (The Pile)

Max Activating Token Index: 22

Text #13

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1892769 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1253796 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1782447 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5937. Min Act: -0.0000

Data Index: 642945 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5930. Min Act: -0.0000

Data Index: 287599 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1684611 (The Pile)

Max Activating Token Index: 358

Text #19

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5876. Min Act: -0.0000

Data Index: 45152 (The Pile)

Max Activating Token Index: 269