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

Dataset: The Pile

Neuron 3125 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1264786 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1132. Min Act: -0.0000

Data Index: 654626 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9897. Min Act: -0.0000

Data Index: 180544 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0647. Min Act: -0.0000

Data Index: 586181 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9299. Min Act: -0.0000

Data Index: 26785 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9719. Min Act: -0.0000

Data Index: 944107 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1758862 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1072589 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1744570 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9851. Min Act: -0.0000

Data Index: 709592 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1934596 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1744934 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1351655 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1828694 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8467. Min Act: -0.0000

Data Index: 818623 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8633. Min Act: -0.0000

Data Index: 748202 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1369277 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1772133 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8779. Min Act: -0.0000

Data Index: 325264 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8570. Min Act: -0.0000

Data Index: 728132 (The Pile)

Max Activating Token Index: 595