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

Dataset: The Pile

Neuron 4409 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: 1.2718. Min Range: -1.2718

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1348705 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1764625 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1061982 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0320. Min Act: -0.0000

Data Index: 856378 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0030. Min Act: -0.0000

Data Index: 796860 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1534518 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1346847 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9598. Min Act: -0.0000

Data Index: 730205 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9848. Min Act: -0.0000

Data Index: 353398 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1372965 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8798. Min Act: -0.0000

Data Index: 780346 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1717968 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9082. Min Act: -0.0000

Data Index: 628841 (The Pile)

Max Activating Token Index: 429

Text #13

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1764362 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1267157 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8984. Min Act: -0.0000

Data Index: 225370 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9094. Min Act: -0.0000

Data Index: 34937 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1400509 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1029029 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8705. Min Act: -0.0000

Data Index: 247783 (The Pile)

Max Activating Token Index: 918