Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.9074. Min Act: -0.0000

Data Index: 1444565 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.9183. Min Act: -0.0000

Data Index: 1888400 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7066. Min Act: -0.0000

Data Index: 881118 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.9544. Min Act: -0.0000

Data Index: 695176 (The Pile)

Max Activating Token Index: 534

Text #4

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1436562 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.7010. Min Act: -0.0000

Data Index: 1694957 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6005. Min Act: -0.0000

Data Index: 1919319 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1043007 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.4902. Min Act: -0.0000

Data Index: 620582 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.4357. Min Act: -0.0000

Data Index: 1368730 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.3175. Min Act: -0.0000

Data Index: 991158 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.5609. Min Act: -0.0000

Data Index: 437557 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1722175 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.3819. Min Act: -0.0000

Data Index: 487616 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1467706 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1745254 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.4287. Min Act: -0.0000

Data Index: 556491 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.3463. Min Act: -0.0000

Data Index: 605890 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.2642. Min Act: -0.0000

Data Index: 198222 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 1.9544. Min Range: -1.9544

Max Act: 1.2052. Min Act: -0.0000

Data Index: 67756 (The Pile)

Max Activating Token Index: 631