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

Dataset: The Pile

Neuron 4014 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: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 287481 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 517577 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 510921 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 456288 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 76878 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 451817 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 406592 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 332966 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 320484 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 76393 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 50718 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 102275 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 286757 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 55934 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 284649 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 253876 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 193874 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 38956 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 168359 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0000

Data Index: 96802 (The Pile)

Max Activating Token Index: 1