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

Dataset: The Pile

Neuron 2192 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.4615. Min Act: -0.0000

Data Index: 579704 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.1841. Min Act: -0.0000

Data Index: 51946 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1711126 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1328640 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.0128. Min Act: -0.0000

Data Index: 1142192 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.0987. Min Act: -0.0000

Data Index: 320641 (The Pile)

Max Activating Token Index: 649

Text #6

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.0870. Min Act: -0.0000

Data Index: 900353 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9951. Min Act: -0.0000

Data Index: 468324 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9838. Min Act: -0.0000

Data Index: 380025 (The Pile)

Max Activating Token Index: 809

Text #9

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.0023. Min Act: -0.0000

Data Index: 246061 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1730276 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9706. Min Act: -0.0000

Data Index: 755994 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.8663. Min Act: -0.0000

Data Index: 724040 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.8647. Min Act: -0.0000

Data Index: 316108 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9464. Min Act: -0.0000

Data Index: 902115 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1923011 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1254193 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.9185. Min Act: -0.0000

Data Index: 135695 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.8584. Min Act: -0.0000

Data Index: 977715 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 1.4615. Min Range: -1.4615

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1985686 (The Pile)

Max Activating Token Index: 245