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

Dataset: The Pile

Neuron 3252 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 69397 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 238685 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1782373 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 766737 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 647390 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1712059 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 440512 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 183128 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1142070 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1786445 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 128133 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 308357 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1383083 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 651890 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 886692 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 475476 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1796020 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1218248 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1766907 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1631869 (The Pile)

Max Activating Token Index: 1