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

Dataset: The Pile

Neuron 662 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7672. Min Act: -0.0000

Data Index: 1294576 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.5816. Min Act: -0.0000

Data Index: 1804069 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.6478. Min Act: -0.0000

Data Index: 244069 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1528320 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7892. Min Act: -0.0000

Data Index: 182611 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1604052 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1534097 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1609954 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1465658 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.5138. Min Act: -0.0000

Data Index: 477776 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1146252 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.2971. Min Act: -0.0000

Data Index: 253264 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.4623. Min Act: -0.0000

Data Index: 198283 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.3356. Min Act: -0.0000

Data Index: 201168 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1820477 (The Pile)

Max Activating Token Index: 414

Text #15

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1601203 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.5001. Min Act: -0.0000

Data Index: 775116 (The Pile)

Max Activating Token Index: 758

Text #17

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.4086. Min Act: -0.0000

Data Index: 162989 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.3165. Min Act: -0.0000

Data Index: 1249581 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1380312 (The Pile)

Max Activating Token Index: 731