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

Dataset: The Pile

Neuron 3983 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: 1.4094. Min Range: -1.4094

Max Act: 1.4094. Min Act: -0.0000

Data Index: 511417 (The Pile)

Max Activating Token Index: 918

Text #1

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1906401 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0948. Min Act: -0.0000

Data Index: 329736 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.1035. Min Act: -0.0000

Data Index: 507957 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1952407 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9399. Min Act: -0.0000

Data Index: 785785 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1825713 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1438094 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1291243 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1190257 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8897. Min Act: -0.0000

Data Index: 389479 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8833. Min Act: -0.0000

Data Index: 618509 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1787921 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8674. Min Act: -0.0000

Data Index: 211681 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1318449 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1590069 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1902714 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1059308 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1731282 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1012233 (The Pile)

Max Activating Token Index: 967