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

Dataset: The Pile

Neuron 3508 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: 1.0724. Min Range: -1.0724

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1941254 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 1.0724. Min Range: -1.0724

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1471256 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8222. Min Act: -0.0000

Data Index: 160668 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1724254 (The Pile)

Max Activating Token Index: 833

Text #4

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.9237. Min Act: -0.0000

Data Index: 702993 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7124. Min Act: -0.0000

Data Index: 732640 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8680. Min Act: -0.0000

Data Index: 754071 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7884. Min Act: -0.0000

Data Index: 253653 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7853. Min Act: -0.0000

Data Index: 271379 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7025. Min Act: -0.0000

Data Index: 210237 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.6273. Min Act: -0.0000

Data Index: 832485 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.7194. Min Act: -0.0000

Data Index: 123377 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.6556. Min Act: -0.0000

Data Index: 205048 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1408112 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.8723. Min Act: -0.0000

Data Index: 788725 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.5142. Min Act: -0.0000

Data Index: 868791 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1094393 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.5242. Min Act: -0.0000

Data Index: 560450 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1283171 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 1.0724. Min Range: -1.0724

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1018031 (The Pile)

Max Activating Token Index: 642