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

Dataset: The Pile

Neuron 3699 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: 1.4090. Min Range: -1.4090

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1896853 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.4090. Min Act: -0.0000

Data Index: 161187 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0913. Min Act: -0.0000

Data Index: 349999 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0111. Min Act: -0.0000

Data Index: 65385 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0580. Min Act: -0.0000

Data Index: 251875 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1689598 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1744. Min Act: -0.0000

Data Index: 361575 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1145769 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9074. Min Act: 0.0000

Data Index: 1084759 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9957. Min Act: -0.0000

Data Index: 558959 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8316. Min Act: 0.0000

Data Index: 443723 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.7731. Min Act: -0.0000

Data Index: 817127 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1328135 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1800446 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9034. Min Act: -0.0000

Data Index: 87709 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8003. Min Act: -0.0000

Data Index: 742524 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8052. Min Act: -0.0000

Data Index: 299264 (The Pile)

Max Activating Token Index: 897

Text #17

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.7972. Min Act: -0.0000

Data Index: 804670 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8140. Min Act: -0.0000

Data Index: 507589 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1040979 (The Pile)

Max Activating Token Index: 640