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

Dataset: The Pile

Neuron 4224 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1036411 (The Pile)

Max Activating Token Index: 702

Text #1

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1332331 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1851721 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1120969 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1081. Min Act: -0.0000

Data Index: 699513 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1071. Min Act: -0.0000

Data Index: 800575 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1021. Min Act: 0.0000

Data Index: 35311 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1537802 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1571626 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1658631 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0968. Min Act: 0.0000

Data Index: 1150792 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0956. Min Act: -0.0000

Data Index: 914413 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0983. Min Act: -0.0000

Data Index: 209955 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1695759 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0904. Min Act: -0.0000

Data Index: 650464 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0875. Min Act: 0.0000

Data Index: 1550039 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1090424 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0906. Min Act: -0.0000

Data Index: 792242 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1754753 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1207404 (The Pile)

Max Activating Token Index: 441