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

Dataset: The Pile

Neuron 437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.2684. Min Act: -0.0000

Data Index: 595510 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.2599. Min Act: -0.0000

Data Index: 1971844 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.1136. Min Act: -0.0000

Data Index: 1738627 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.1173. Min Act: -0.0000

Data Index: 543337 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.1062. Min Act: -0.0000

Data Index: 1853393 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.0619. Min Act: -0.0000

Data Index: 697663 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.0384. Min Act: -0.0000

Data Index: 1067336 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.0368. Min Act: -0.0000

Data Index: 929502 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.9520. Min Act: -0.0000

Data Index: 1504317 (The Pile)

Max Activating Token Index: 885

Text #9

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.8036. Min Act: -0.0000

Data Index: 1608272 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.9242. Min Act: -0.0000

Data Index: 130968 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 3.2684. Min Range: -3.2684

Max Act: 3.0429. Min Act: -0.0000

Data Index: 1350746 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.7311. Min Act: -0.0000

Data Index: 1234082 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.8384. Min Act: -0.0000

Data Index: 734341 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.6975. Min Act: -0.0000

Data Index: 1630121 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.8431. Min Act: -0.0000

Data Index: 1495385 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.7894. Min Act: -0.0000

Data Index: 1056330 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.7914. Min Act: -0.0000

Data Index: 292474 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.7876. Min Act: -0.0000

Data Index: 36009 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 3.2684. Min Range: -3.2684

Max Act: 2.7627. Min Act: -0.0000

Data Index: 506459 (The Pile)

Max Activating Token Index: 310