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

Dataset: The Pile

Neuron 2789 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: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1000265 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 212648 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 8529 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 382733 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 470101 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1018752 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 750339 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1738 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 71000 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 287831 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 514185 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 897058 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 87828 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 927267 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 64082 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 611538 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 856167 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1040907 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1034824 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1165 (The Pile)

Max Activating Token Index: 1