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

Dataset: The Pile

Neuron 4997 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.9647. Min Act: -0.0000

Data Index: 573630 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1297330 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7876. Min Act: -0.0000

Data Index: 4257 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1053949 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7741. Min Act: -0.0000

Data Index: 805510 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1465302 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1327862 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1866552 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7261. Min Act: -0.0000

Data Index: 375616 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7270. Min Act: -0.0000

Data Index: 103782 (The Pile)

Max Activating Token Index: 866

Text #10

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6574. Min Act: -0.0000

Data Index: 35982 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6952. Min Act: 0.0000

Data Index: 794310 (The Pile)

Max Activating Token Index: 615

Text #12

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1028814 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1073391 (The Pile)

Max Activating Token Index: 497

Text #14

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8038. Min Act: -0.0000

Data Index: 539782 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6960. Min Act: 0.0000

Data Index: 287382 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1478457 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6642. Min Act: 0.0000

Data Index: 813781 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6615. Min Act: 0.0000

Data Index: 1028963 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1085112 (The Pile)

Max Activating Token Index: 121