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

Dataset: The Pile

Neuron 321 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1596034 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1740952 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8143. Min Act: -0.0000

Data Index: 709790 (The Pile)

Max Activating Token Index: 711

Text #3

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6687. Min Act: -0.0000

Data Index: 909817 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7987. Min Act: -0.0000

Data Index: 585746 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8540. Min Act: -0.0000

Data Index: 317259 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1530374 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7472. Min Act: -0.0000

Data Index: 665542 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6379. Min Act: -0.0000

Data Index: 422743 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7636. Min Act: -0.0000

Data Index: 431700 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7131. Min Act: -0.0000

Data Index: 763317 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1794986 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1134068 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1267794 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7580. Min Act: -0.0000

Data Index: 610105 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1762944 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1736903 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6507. Min Act: -0.0000

Data Index: 539837 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7579. Min Act: -0.0000

Data Index: 270166 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1243937 (The Pile)

Max Activating Token Index: 366