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

Dataset: The Pile

Neuron 2601 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: 0.8093. Min Range: -0.8093

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1797961 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.8009. Min Act: -0.0000

Data Index: 997291 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.7378. Min Act: -0.0000

Data Index: 191460 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.8093. Min Act: -0.0000

Data Index: 369308 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1900203 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5442. Min Act: -0.0000

Data Index: 935385 (The Pile)

Max Activating Token Index: 757

Text #6

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6705. Min Act: -0.0000

Data Index: 324491 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6094. Min Act: -0.0000

Data Index: 380376 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5807. Min Act: -0.0000

Data Index: 973915 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5952. Min Act: -0.0000

Data Index: 400510 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1134677 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5846. Min Act: -0.0000

Data Index: 813832 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5935. Min Act: -0.0000

Data Index: 812295 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1266876 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6112. Min Act: -0.0000

Data Index: 626857 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5695. Min Act: -0.0000

Data Index: 314101 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1613707 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5735. Min Act: -0.0000

Data Index: 406577 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1174247 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.8093. Min Range: -0.8093

Max Act: 0.5451. Min Act: -0.0000

Data Index: 28646 (The Pile)

Max Activating Token Index: 149