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

Dataset: The Pile

Neuron 1624 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: 5.5644. Min Range: -5.5644

Max Act: 5.5644. Min Act: -0.0000

Data Index: 1384357 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.4298. Min Act: -0.0000

Data Index: 1142238 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.2040. Min Act: -0.0000

Data Index: 1355042 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.1823. Min Act: -0.0000

Data Index: 619907 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.3002. Min Act: -0.0000

Data Index: 317404 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.0928. Min Act: -0.0000

Data Index: 1812901 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.1988. Min Act: -0.0000

Data Index: 178707 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.1655. Min Act: -0.0000

Data Index: 400169 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.0922. Min Act: -0.0000

Data Index: 1077084 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.0249. Min Act: -0.0000

Data Index: 1374889 (The Pile)

Max Activating Token Index: 697

Text #10

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.0399. Min Act: -0.0000

Data Index: 1601000 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 5.5644. Min Range: -5.5644

Max Act: 5.2584. Min Act: -0.0000

Data Index: 123524 (The Pile)

Max Activating Token Index: 11

Text #12

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.9904. Min Act: -0.0000

Data Index: 1438226 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.9659. Min Act: -0.0000

Data Index: 1206264 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.9050. Min Act: -0.0000

Data Index: 984334 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.8906. Min Act: -0.0000

Data Index: 513582 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.9080. Min Act: -0.0000

Data Index: 508181 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.8919. Min Act: -0.0000

Data Index: 296644 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.6829. Min Act: -0.0000

Data Index: 1402405 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 5.5644. Min Range: -5.5644

Max Act: 4.8314. Min Act: -0.0000

Data Index: 1586800 (The Pile)

Max Activating Token Index: 4